© 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. 21-GEMMASCOPE-RES-16K
    6. 1070
    Prev
    Next
    INDEX
    Explanations

    patterns in sequential or structured data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    Hentet
    -0.65
     VizieR
    -0.64
    mtrl
    -0.60
    PyExc
    -0.58
    stateMutability
    -0.58
    drawSprites
    -0.57
    twimg
    -0.57
    InvalidProtocol
    -0.57
     Roskov
    -0.56
    AndroidJUnit
    -0.54
    POSITIVE LOGITS
    :+:
    0.73
     يتيمه
    0.63
    δώ
    0.53
    TokenNameLBRACE
    0.52
     disambiguazione
    0.52
    ossi
    0.49
    tagHelperRunner
    0.49
    chaun
    0.47
     devenus
    0.46
    copal
    0.45
    Activations Density 0.062%

    No Known Activations