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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 390
    Prev
    Next
    INDEX
    Explanations

    mechanical components and their related functions.

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

    scientific and technical descriptions related to medical devices and food processing.

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

    words or phrases related to physical attachment or connection, particularly in mechanical or technical contexts.

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

    "attached to"

    np_acts-logits-general · gemini-2.0-flash

    attached to

    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
     cellpadding
    -0.55
    CodedInputStream
    -0.51
     alley
    -0.50
     refraction
    -0.50
     cono
    -0.47
     stuffing
    -0.46
    crow
    -0.46
    eeq
    -0.46
     Quis
    -0.45
     gaps
    -0.45
    POSITIVE LOGITS
     Attach
    0.97
     attach
    0.95
     attaches
    0.93
     attaching
    0.90
     attachments
    0.90
     Attachments
    0.84
     attachment
    0.83
     ATTACH
    0.82
    attach
    0.81
    Attach
    0.80
    Activations Density 0.201%

    No Known Activations