© 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. 11672
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases that indicate a focus on individual contributions or data points

    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
    неопр
    -0.56
     nakalista
    -0.55
     confirm
    -0.53
    GeoNames
    -0.53
    XtraReports
    -0.52
    VersionUID
    -0.50
     PyTuple
    -0.48
    Vorlage
    -0.47
     ibid
    -0.47
    confirm
    -0.47
    POSITIVE LOGITS
    Each
    1.41
     Each
    1.37
     Cada
    1.30
    Chaque
    1.28
    Cada
    1.24
    Каждый
    1.22
    each
    1.21
    EACH
    1.20
     Ogni
    1.19
    Ogni
    1.18
    Activations Density 0.235%

    No Known Activations