© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3480
    Prev
    Next
    INDEX
    Explanations

    programming and technical terms related to data structures and options management

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

    Code, variables, or data structures

    np_acts-logits-general · gemini-2.0-flash

    codes ending with punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     void
    -0.57
    -------------</
    -0.51
    ες
    -0.49
    ()][
    -0.49
     N
    -0.46
    >::
    -0.46
    void
    -0.44
     Ind
    -0.43
     best
    -0.43
    _))
    -0.43
    POSITIVE LOGITS
     purpoſe
    0.94
     Monfieur
    0.93
     ſeveral
    0.88
     Reſ
    0.88
     Majefty
    0.88
     Anſ
    0.86
     reaſon
    0.86
     myſelf
    0.85
     Eſ
    0.85
     fevere
    0.84
    Activations Density 0.163%

    No Known Activations