© 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. 15373
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms related to legal and technical contexts

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

    Letters followed by brackets

    np_acts-logits-general · gemini-2.0-flash

    audio, available, access, activity

    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
    TabStop
    -0.61
     مشين
    -0.59
    ailles
    -0.50
     Kell
    -0.48
    htbp
    -0.44
    urfs
    -0.42
     nearest
    -0.42
    whip
    -0.42
     Scherer
    -0.42
    ensa
    -0.41
    POSITIVE LOGITS
    nother
    0.59
    ctivity
    0.59
    uto
    0.58
    ppell
    0.55
    CrossRef
    0.54
    chie
    0.54
    gain
    0.53
    udio
    0.52
    UDIO
    0.51
    mazing
    0.51
    Activations Density 0.218%

    No Known Activations