© 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. 1704
    Prev
    Next
    INDEX
    Explanations

    key procedural details and important numerical elements in scientific or technical contexts

    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
    WebVitals
    -0.62
    XmlEnum
    -0.50
    laşı
    -0.43
    Personendaten
    -0.43
     InputDecoration
    -0.42
    verwijspagina
    -0.42
    frente
    -0.41
    zzleHttp
    -0.40
    gonic
    -0.40
    IVEREF
    -0.40
    POSITIVE LOGITS
     second
    3.41
    second
    3.04
    Second
    2.84
     secondly
    2.73
     Second
    2.68
     SECOND
    2.64
    SECOND
    2.49
     Secondly
    2.48
     seconde
    2.42
    Secondly
    2.40
    Activations Density 0.761%

    No Known Activations