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. 16-GEMMASCOPE-RES-16K
    6. 14854
    Prev
    Next
    INDEX
    Explanations

    references to committees and hearings in a legislative context

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

    a committee or committees

    np_acts-logits-general · gemini-2.0-flash

    committee

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ceutical
    -0.65
    ations
    -0.64
    mals
    -0.62
    azz
    -0.59
     Ost
    -0.58
     Byron
    -0.57
     Rox
    -0.57
    ization
    -0.57
    afar
    -0.56
    scal
    -0.56
    POSITIVE LOGITS
    committees
    1.28
     committees
    1.20
     Committees
    1.17
     Bourke
    0.93
    committee
    0.92
     Volga
    0.92
    AnchorStyles
    0.91
     COMMITTEE
    0.90
     CreateTagHelper
    0.90
     komis
    0.90
    Activations Density 0.119%

    No Known Activations