© 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. 30-GEMMASCOPE-RES-16K
    11. 15194
    Prev
    Next
    INDEX
    Explanations

    instances of "and" or conjunctions linking multiple entities or ideas

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

    people/entities with "and" or "&"

    np_acts-logits-general · gemini-2.0-flash

    and I

    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
    -0.66
     próprios
    -0.62
    sandalia
    -0.61
    Сылтамалар
    -0.61
     SwitchCompat
    -0.59
     arvio
    -0.58
     amortecedor
    -0.57
    Чыганаклар
    -0.57
     propios
    -0.57
    seamnă
    -0.56
    POSITIVE LOGITS
     others
    0.75
    others
    0.60
     Others
    0.57
     colleagues
    0.55
    Others
    0.52
     OTHERS
    0.48
     crew
    0.45
     his
    0.45
    ########.
    0.45
     fellow
    0.44
    Activations Density 0.250%

    No Known Activations