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. 8348
    Prev
    Next
    INDEX
    Explanations

    occurrences of the forward slash symbol

    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
    "]
    
    -0.51
    OIR
    -0.51
    OnTop
    -0.46
     Triton
    -0.45
     ripples
    -0.44
     Arcadia
    -0.44
     atrial
    -0.44
    हर
    -0.44
     capes
    -0.43
     surveyors
    -0.43
    POSITIVE LOGITS
     GenerationType
    1.20
     للمعارف
    1.05
    bootstrapcdn
    0.99
    NamedQueries
    0.93
    %/
    0.90
     ostavi
    0.90
    jsdelivr
    0.85
    таратура
    0.83
    XmlAccessorType
    0.81
    ----</
    0.81
    Activations Density 0.206%

    No Known Activations