Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 7772
    Prev
    Next
    INDEX
    Explanations

    key legal and jurisdictional references

    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
    érience
    -0.35
     dė
    -0.34
    tú
    -0.33
     tú
    -0.33
     Offisielt
    -0.33
    Lähteet
    -0.33
     gruesa
    -0.32
     étranger
    -0.32
     popoli
    -0.31
    LayoutStyle
    -0.31
    POSITIVE LOGITS
     Arkansas
    1.30
    Arkansas
    1.21
     ARK
    0.84
     ark
    0.81
     Ark
    0.80
     Ozark
    0.80
     Razor
    0.77
    Ark
    0.77
     Fayetteville
    0.77
    ARK
    0.71
    Activations Density 0.313%

    No Known Activations