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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16115
    Prev
    Next
    INDEX
    Explanations

    characters and symbols used in mathematical representations and functions

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

    "Q" followed by another character

    np_acts-logits-general · gemini-2.0-flash

    words starting with q or Q

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnimationsModule
    -0.44
    eland
    -0.43
     ControllerBase
    -0.38
    DateTimeFormat
    -0.36
    สึก
    -0.35
    ApiModelProperty
    -0.35
     lander
    -0.35
     bors
    -0.35
    RenderAtEndOf
    -0.35
     Eden
    -0.34
    POSITIVE LOGITS
     Q
    1.11
    Q
    0.94
     Queen
    0.88
     q
    0.88
     QUEEN
    0.87
     Queensland
    0.86
     quantum
    0.85
     Quezon
    0.84
     queen
    0.82
     Quentin
    0.82
    Activations Density 0.259%

    No Known Activations