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. 6155
    Prev
    Next
    INDEX
    Explanations

    references to desires and fundamental human needs

    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
    .
    -0.56
    تها
    -0.54
     to
    -0.51
     
    -0.51
    tamanya
    -0.51
     (
    -0.50
     when
    -0.47
    ,
    -0.47
    '
    -0.47
    UVWXYZ
    -0.47
    POSITIVE LOGITS
    onViewCreated
    0.82
     ―――――
    0.79
     متعلقه
    0.77
     Efq
    0.75
     propOrder
    0.74
     ſy
    0.74
    ^(@)
    0.73
     itſelf
    0.73
     Eſ
    0.73
     của
    0.73
    Activations Density 0.896%

    No Known Activations