© 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. 3795
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or "spots" in various contexts

    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
     Maier
    -0.76
    íncia
    -0.71
    weetened
    -0.69
     Ayres
    -0.67
    hiva
    -0.66
    PROTOBUF
    -0.66
    thyroidism
    -0.65
     Mala
    -0.65
    ณา
    -0.65
     familiari
    -0.64
    POSITIVE LOGITS
     spot
    3.03
     Spot
    2.85
    spot
    2.67
     SPOT
    2.65
    Spot
    2.62
     spots
    2.61
     Spots
    2.55
    spots
    2.41
    SPOT
    2.41
    Spots
    2.08
    Activations Density 0.037%

    No Known Activations