© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 7079
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to technical or logical parameters in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iastes
    -0.69
    inburgh
    -0.68
    ängel
    -0.68
    rogels
    -0.66
    atów
    -0.66
     Hermans
    -0.65
    dersfield
    -0.65
    jména
    -0.64
    WireFormatLite
    -0.63
    aarrggbb
    -0.63
    POSITIVE LOGITS
    styleType
    0.71
    WithIdentifier
    0.66
    OrBuilder
    0.63
    deutscher
    0.60
     AssemblyVersion
    0.60
     Vele
    0.59
    iais
    0.58
    
    0.58
    INCREF
    0.57
    ными
    0.57
    Activations Density 0.034%

    No Known Activations