Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11976
    Prev
    Next
    INDEX
    Explanations

    references to statistical data or numerical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.83
    SharedDtor
    -0.72
    httphttps
    -0.65
     nakalista
    -0.64
    Hentet
    -0.63
    +#+#
    -0.58
    Tikang
    -0.56
    tvguidetime
    -0.54
    providedIn
    -0.54
    InputBorder
    -0.53
    POSITIVE LOGITS
     none
    0.39
     Likewise
    0.37
    Likewise
    0.36
     corresponding
    0.36
     fehlen
    0.36
     counterparts
    0.35
     hias
    0.35
    เดิม
    0.34
     correspondingly
    0.34
     counterpart
    0.33
    Activations Density 0.813%

    No Known Activations