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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 8085
    Prev
    Next
    INDEX
    Explanations

    specific functions or methods related to software or coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -0.58
     something
    -0.53
     of
    -0.49
     for
    -0.47
     in
    -0.43
     I
    -0.43
     that
    -0.42
     which
    -0.42
     with
    -0.42
     around
    -0.41
    POSITIVE LOGITS
    neſs
    1.10
     Efq
    1.09
     itſelf
    1.08
    ſelf
    1.06
     ་་
    1.06
     $_"
    1.05
     Chriftian
    1.03
     ―――――
    1.01
     Majefty
    1.00
     Jefus
    1.00
    Activations Density 0.434%

    No Known Activations