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. 11-GEMMASCOPE-RES-16K
    6. 1655
    Prev
    Next
    INDEX
    Explanations

    topics related to murder or homicide in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portale
    -0.80
     CreateTagHelper
    -0.78
    InjectAttribute
    -0.76
    enumi
    -0.73
    __(/*!
    -0.73
    клопе
    -0.71
    FunctionFlags
    -0.70
    MemoryWarning
    -0.67
     الاطلاع
    -0.65
    شهاد
    -0.63
    POSITIVE LOGITS
    feof
    0.48
     etter
    0.46
     local
    0.42
     locals
    0.40
     après
    0.39
     after
    0.39
    DriverManager
    0.38
    onerror
    0.38
     nahilalakip
    0.38
    例句
    0.36
    Activations Density 0.109%

    No Known Activations