© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5953
    Prev
    Next
    INDEX
    Explanations

    references to specific classifications or types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnsafeEnabled
    -0.91
     nicio
    -0.85
     sternum
    -0.77
    sizeCache
    -0.76
     strconv
    -0.74
    ceuticals
    -0.73
     McCullough
    -0.72
     ',',
    -0.71
     [];
    -0.69
    IsPostBack
    -0.68
    POSITIVE LOGITS
     type
    2.85
     Type
    2.70
     TYPE
    2.59
     types
    2.48
    type
    2.40
    Type
    2.23
    TYPE
    2.19
     tipo
    2.16
     Types
    2.08
    types
    2.05
    Activations Density 0.148%

    No Known Activations