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. 8-GEMMASCOPE-RES-16K
    6. 8514
    Prev
    Next
    INDEX
    Explanations

    the presence of introductory phrases and statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nextProps
    -1.16
    CloseOperation
    -1.08
     ſeveral
    -0.92
    httphttps
    -0.90
     ſever
    -0.89
     propOrder
    -0.88
    tableFuture
    -0.87
     Houſe
    -0.85
     BoxDecoration
    -0.85
     houſe
    -0.83
    POSITIVE LOGITS
     Is
    1.29
    Is
    1.22
     IS
    1.22
     setIs
    1.10
    bIs
    1.05
    mIs
    1.02
    is
    1.01
    IS
    1.01
     is
    1.00
     Ishi
    0.89
    Activations Density 0.140%

    No Known Activations