© 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. 13-GEMMASCOPE-RES-16K
    11. 8636
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the act of referencing or citing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oustic
    -0.51
    athus
    -0.49
    انتهای
    -0.49
    ghum
    -0.48
    umenten
    -0.47
    jublj
    -0.46
    OGLYPH
    -0.45
    ulent
    -0.44
     Alg
    -0.44
     fluff
    -0.43
    POSITIVE LOGITS
    see
    1.45
     see
    1.38
    See
    1.32
     See
    1.31
     SEE
    1.17
    SEE
    1.12
     sees
    0.96
     siehe
    0.93
    siehe
    0.88
    Seen
    0.85
    Activations Density 0.138%

    No Known Activations