© 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. 14246
    Prev
    Next
    INDEX
    Explanations

    quotation marks and dialogue

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

    Followed by a quote

    np_acts-logits-general · gemini-2.0-flash

    quotation marks

    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
    Personendaten
    -1.12
    ðsíða
    -1.09
    expandindo
    -1.09
    majánló
    -1.07
    ſehen
    -1.05
    ſicht
    -1.05
    ſchaft
    -1.04
     fashiola
    -1.03
     zwiſchen
    -1.03
    ésultats
    -1.02
    POSITIVE LOGITS
    There
    0.73
    They
    0.69
    The
    0.68
    This
    0.68
    It
    0.65
    I
    0.65
    We
    0.60
    That
    0.58
    For
    0.57
    When
    0.56
    Activations Density 0.111%

    No Known Activations