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. 7-GEMMASCOPE-RES-16K
    6. 9410
    Prev
    Next
    INDEX
    Explanations

    terms related to various forms of classification and comparison

    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
     laikā
    -0.53
    мена
    -0.53
     &___
    -0.51
    colato
    -0.51
    encodeWith
    -0.50
    icycles
    -0.50
    MessageOf
    -0.50
    IGraphics
    -0.49
    setFont
    -0.48
    ruka
    -0.47
    POSITIVE LOGITS
     esternos
    0.89
     contender
    0.83
     banger
    0.83
     Majefty
    0.83
     newbies
    0.82
     Efq
    0.82
     contenders
    0.81
     outliers
    0.79
     Jefus
    0.77
     classics
    0.77
    Activations Density 0.507%

    No Known Activations