© 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. 4-GEMMASCOPE-RES-16K
    11. 946
    Prev
    Next
    INDEX
    Explanations

    numeric values and their conversions relating to data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NOPQRST
    -0.81
     GenerationType
    -0.77
    MigrationBuilder
    -0.70
    })()
    -0.68
    sterious
    -0.67
    abetes
    -0.66
     Lindgren
    -0.66
    neſs
    -0.66
     ActivatedRoute
    -0.66
    sieur
    -0.65
    POSITIVE LOGITS
    TagMode
    0.63
    Eloquent
    0.43
     ...
    0.43
     CYTHON
    0.43
    折
    0.42
    Trading
    0.42
    格
    0.41
    ↵↵
    0.40
    Catching
    0.39
    ---
    0.38
    Activations Density 1.276%

    No Known Activations