© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15220
    Prev
    Next
    INDEX
    Explanations

    words related to societal and political perspectives.

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    information related to history and politics.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases referring to a place or region, often using the structure "the land of..." or similar constructions.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Follows the word "of"

    np_acts-logits-general · gemini-2.0-flash

    of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIOException
    -0.48
     AssemblyCulture
    -0.42
     prosent
    -0.40
     an
    -0.40
    vaiz
    -0.40
     zufolge
    -0.39
    fas
    -0.39
    intero
    -0.38
    DB
    -0.38
    IUrlHelper
    -0.38
    POSITIVE LOGITS
    ArgsConstructor
    0.81
     الحره
    0.74
     Roskov
    0.73
     miracles
    0.69
     illusions
    0.68
    AndEndTag
    0.68
     Possibilities
    0.68
     horrors
    0.67
    Personendaten
    0.67
     acronyms
    0.67
    Activations Density 0.144%

    No Known Activations