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. 15-GEMMASCOPE-RES-16K
    6. 2719
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to court proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DebuggerStep
    -0.72
    archiviato
    -0.58
     useAppContext
    -0.55
     '\\;'
    -0.53
    jsdelivr
    -0.49
    Dichloropropene
    -0.49
    OGND
    -0.48
    Américaine
    -0.48
    permitAll
    -0.48
    mergeFrom
    -0.48
    POSITIVE LOGITS
    Vidite
    0.69
    setVerticalGroup
    0.69
    WebElementEntity
    0.61
    IntoConstraints
    0.59
     rarement
    0.58
    中略
    0.57
     estekak
    0.56
     aikaa
    0.56
     solito
    0.56
     Мексичка
    0.55
    Activations Density 1.097%

    No Known Activations