Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10440
    Prev
    Next
    INDEX
    Explanations

    code structures related to function declarations and interface definitions in TypeScript

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

    Code syntax or special characters

    np_acts-logits-general · gemini-2.0-flash

    sank behind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новништво
    -0.51
    ))->
    -0.46
     penanganan
    -0.43
    XPATH
    -0.43
    /'+
    -0.43
    querque
    -0.42
    цій
    -0.42
    ++$
    -0.41
    Quercus
    -0.41
    ))){
    -0.40
    POSITIVE LOGITS
     |
    0.72
    |
    0.66
     Efq
    0.65
     $|
    0.65
     étoit
    0.60
    }|
    0.60
     Monfieur
    0.60
    ⎮
    0.59
     tslint
    0.59
    [];
    0.59
    Activations Density 0.077%

    No Known Activations