© 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. 22-GEMMASCOPE-RES-16K
    6. 8921
    Prev
    Next
    INDEX
    Explanations

    specific acronyms and identifiers related to scientific and technical contexts

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

    Three-letter acronyms

    np_acts-logits-general · gemini-2.0-flash

    acronyms followed by common nouns

    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
     nakalista
    -0.66
     تانيه
    -0.63
    onaceous
    -0.60
    subpackage
    -0.59
    usermodel
    -0.58
    TargetException
    -0.58
    paksa
    -0.58
    setupUi
    -0.58
     saites
    -0.58
    #
    -0.57
    POSITIVE LOGITS
     meriva
    0.77
     Anſ
    0.70
     ſame
    0.69
     ainfi
    0.69
     Diſ
    0.69
     dezelve
    0.69
     auffi
    0.68
     ['$
    0.66
     zelve
    0.66
     Inscrivez
    0.65
    Activations Density 0.766%

    No Known Activations