© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 12589
    Prev
    Next
    INDEX
    Explanations

    commands related to maintenance or repair tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 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
     épaules
    -0.60
     gynhyrchwyd
    -0.60
     verspre
    -0.59
     collè
    -0.59
     réunis
    -0.56
     picioare
    -0.54
     cappello
    -0.54
     genoux
    -0.53
     écrits
    -0.53
     prêts
    -0.53
    POSITIVE LOGITS
     replace
    0.83
     replaced
    0.76
     replacing
    0.73
     disassemble
    0.71
     replaces
    0.68
     install
    0.67
     uns
    0.66
     propOrder
    0.66
    +#+
    0.66
     installed
    0.65
    Activations Density 0.165%

    No Known Activations