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. 5615
    Prev
    Next
    INDEX
    Explanations

    references to boards, board members, and board-related positions

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

    "board member" or mentions of "the board"

    np_acts-logits-general · gemini-2.0-flash

    board member or boardroom

    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
    فحة
    -0.69
    rious
    -0.61
     Privacidade
    -0.56
    ]-->
    -0.55
    UARY
    -0.55
    ../../
    -0.55
    ']?>
    -0.55
    ณ์
    -0.54
    ahuje
    -0.54
    )))));
    -0.53
    POSITIVE LOGITS
    room
    0.76
    er
    0.74
    walks
    0.71
     Member
    0.69
    inghouse
    0.69
    member
    0.67
    boards
    0.67
    walk
    0.66
     member
    0.66
     boards
    0.64
    Activations Density 0.053%

    No Known Activations