© 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. 18-GEMMASCOPE-RES-16K
    11. 1932
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a change in state or action depending on context

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

    Following the word "on"

    np_acts-logits-general · gemini-2.0-flash

    on a, on the, on top

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DebuggerNonUser
    -0.72
     gynnwys
    -0.55
    ruimte
    -0.51
    脚注の使い方
    -0.51
    Beijinhos
    -0.50
    standers
    -0.50
    Personendaten
    -0.49
    WhereInput
    -0.48
     citer
    -0.48
    katapos
    -0.48
    POSITIVE LOGITS
     kasarigan
    0.64
    icial
    0.63
    ValueStyle
    0.60
    DeleteBehavior
    0.58
     offense
    0.55
    skem
    0.53
     مشين
    0.53
     Sunday
    0.51
    RenderAtEndOf
    0.51
    gwick
    0.51
    Activations Density 0.210%

    No Known Activations