© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 13063
    Prev
    Next
    INDEX
    Explanations

    terms related to science fiction and diverse publishing references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Italian or Spanish words

    np_acts-logits-general · gemini-2.0-flash

    numbers ending in `ica` or `io`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pecabe
    -1.08
     gruesa
    -1.02
     plateado
    -1.01
     colgante
    -0.98
     fieltro
    -0.98
     rodillas
    -0.94
     valentín
    -0.93
     templado
    -0.93
     capitán
    -0.91
     Atlántico
    -0.91
    POSITIVE LOGITS
     seta
    0.65
     inci
    0.59
     viti
    0.57
     prover
    0.57
     quo
    0.57
     coco
    0.56
     quanta
    0.56
     astra
    0.55
     insu
    0.55
     sequ
    0.54
    Activations Density 0.030%

    No Known Activations