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. 19-GEMMASCOPE-RES-16K
    6. 2747
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to markets and their dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aime
    -0.55
    GGGG
    -0.54
    TypeDef
    -0.54
     Италијани
    -0.53
    consin
    -0.51
    )_{
    -0.50
    +#+
    -0.49
    hips
    -0.48
     виправивши
    -0.47
    sos
    -0.47
    POSITIVE LOGITS
    Markets
    0.98
    places
    0.96
     markets
    0.95
    PLACE
    0.91
    markets
    0.87
     Markets
    0.85
     place
    0.83
    Place
    0.78
     markt
    0.77
    place
    0.76
    Activations Density 0.046%

    No Known Activations