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. 4-GEMMASCOPE-RES-16K
    6. 15853
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fractions
    -0.63
    XmlType
    -0.63
    ValueStyle
    -0.58
     boneca
    -0.56
    duate
    -0.55
     Tré
    -0.55
     aph
    -0.55
    ➟
    -0.54
    ylla
    -0.53
     Demokrat
    -0.52
    POSITIVE LOGITS
    Pyx
    0.62
    ToBounds
    0.62
    EndContext
    0.61
    }}}}
    0.61
    用来
    0.60
    ucoup
    0.59
    forRoot
    0.59
    '])){
    
    0.58
     uintptr
    0.58
    }');
    0.57
    Activations Density 0.254%

    No Known Activations