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

    Neuronpedia

    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. 23-GEMMASCOPE-RES-16K
    11. 1881
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the purpose or context of usage in discussions or technical content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ModelSerializer
    -0.79
    tvguidetime
    -0.71
    دانشنامهٔ
    -0.70
     fashiola
    -0.67
    exitRule
    -0.65
    mtrl
    -0.65
     pouvoit
    -0.65
    曖昧さ回避
    -0.64
     ویکی‌پدی
    -0.63
     Italijani
    -0.63
    POSITIVE LOGITS
     see
    0.56
     details
    0.44
     full
    0.40
     hints
    0.37
     more
    0.35
     See
    0.34
    see
    0.33
     sees
    0.32
     examples
    0.32
     obtain
    0.31
    Activations Density 0.303%

    No Known Activations