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. 4574
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and equations related to statistical processes

    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
    vin
    -0.46
    </b>
    -0.45
    de
    -0.44
    ेन
    -0.43
     PROVIDED
    -0.42
     así
    -0.42
    Provided
    -0.42
     alguna
    -0.42
    Bras
    -0.41
    ier
    -0.41
    POSITIVE LOGITS
    endphp
    0.94
    expandindo
    0.94
     GenerationType
    0.88
     AssemblyCompany
    0.84
     AssemblyTitle
    0.84
     Offisielt
    0.83
    UIControlState
    0.82
     Efq
    0.80
     tartalomajánló
    0.79
     ſmall
    0.79
    Activations Density 0.171%

    No Known Activations