© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 13634
    Prev
    Next
    INDEX
    Explanations

    technical terms and scientific vocabulary related to materials and their properties

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

    syllables or letter combinations in non-English names or technical terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arangay
    -0.85
    pecabe
    -0.84
    alakip
    -0.82
     ainfi
    -0.81
    iffance
    -0.79
    iſen
    -0.78
    ientras
    -0.77
    ambién
    -0.77
    ulongan
    -0.74
    ihnach
    -0.74
    POSITIVE LOGITS
    ers
    0.51
    ing
    0.48
    </sup>
    0.47
      
    0.46
    wapV
    0.45
    <eos>
    0.44
    [toxicity=0]
    0.44
    AxisAlignment
    0.43
    al
    0.43
    jgl
    0.43
    Activations Density 5.280%

    No Known Activations