© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 704
    Prev
    Next
    INDEX
    Explanations

    references to temporal indicators such as days, years, and times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tazama
    -0.52
    MessageOf
    -0.49
    WebElementEntity
    -0.42
    OCCURRED
    -0.42
    IVEREF
    -0.40
    InteropServices
    -0.40
     referenties
    -0.39
    ăzi
    -0.38
    pulumi
    -0.38
     pathways
    -0.38
    POSITIVE LOGITS
     estekak
    0.62
    IsContent
    0.57
     Chwiliwch
    0.54
    complexContent
    0.48
    ValueGenerated
    0.47
     aufs
    0.45
    Ikus
    0.44
    StoryboardSegue
    0.43
    jom
    0.42
    toxicity
    0.41
    Activations Density 0.168%

    No Known Activations