© 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. 27-GEMMASCOPE-RES-16K
    11. 10163
    Prev
    Next
    INDEX
    Explanations

    symbols and indicators of code structure or formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.62
    Parcelize
    -0.61
    InputBorder
    -0.57
    colgroup
    -0.56
    Composable
    -0.54
     <=",
    -0.53
     sumpay
    -0.53
     esterni
    -0.50
     MonoBehaviour
    -0.50
    RTP
    -0.48
    POSITIVE LOGITS
    toxicity
    0.62
    ifiquement
    0.31
     betrek
    0.30
     efficacité
    0.30
     distinctive
    0.30
     betweenstory
    0.29
     dumne
    0.29
     erkek
    0.29
    addPreferredGap
    0.29
    typeDefinition
    0.28
    Activations Density 0.021%

    No Known Activations