© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 9323
    Prev
    Next
    INDEX
    Explanations

    phrases that begin with "As" followed by a numerical value or statement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تانيه
    -0.78
     useParams
    -0.74
    ulity
    -0.74
     addirittura
    -0.72
    truk
    -0.70
    lename
    -0.69
    MessageOf
    -0.69
     ogóle
    -0.67
     ramah
    -0.67
    hema
    -0.67
    POSITIVE LOGITS
    As
    1.48
     As
    1.42
    as
    0.77
     تضيفلها
    0.70
    At
    0.65
    Towards
    0.64
    S
    0.64
     AS
    0.61
     arsenic
    0.60
     Ashland
    0.60
    Activations Density 0.104%

    No Known Activations