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. 19-GEMMASCOPE-RES-16K
    6. 15369
    Prev
    Next
    INDEX
    Explanations

    assignment statements and function calls in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +:+
    -0.61
     للاسماء
    -0.61
    AppRoutingModule
    -0.60
     <<<<<<<<<<<<<<
    -0.60
    mergeFrom
    -0.60
     defStyleAttr
    -0.58
     ddelweddau
    -0.57
    Personensuche
    -0.56
    цима
    -0.55
    rrggbb
    -0.54
    POSITIVE LOGITS
     useState
    1.04
    useState
    0.97
    useEffect
    0.59
    Бахар
    0.59
    WEBPACK
    0.57
    Scénario
    0.55
    findpost
    0.55
     ([]
    0.55
    äischen
    0.54
    fetchone
    0.51
    Activations Density 0.023%

    No Known Activations