© 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. 0-GEMMASCOPE-RES-16K
    11. 9290
    Prev
    Next
    INDEX
    Explanations

    references to biological structures or components related to organs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     montaña
    -0.38
     hiér
    -0.35
     conduite
    -0.35
     corredor
    -0.33
    <bos>
    -0.30
     tjen
    -0.30
    バット
    -0.30
     staat
    -0.29
     licencias
    -0.29
     higher
    -0.29
    POSITIVE LOGITS
     organ
    1.07
    organ
    0.93
     Administrativna
    0.88
     Organ
    0.87
     snippetHide
    0.85
    Organic
    0.84
     nakalista
    0.83
    SequentialGroup
    0.83
    ORGAN
    0.82
     organic
    0.81
    Activations Density 0.201%

    No Known Activations