© 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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105779
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and their quantitative attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.41
    +#+#
    -0.40
    IsContent
    -0.38
    <eos>
    -0.36
     tartalomajánló
    -0.35
    enderror
    -0.35
     Flats
    -0.34
     especial
    -0.34
     ramos
    -0.32
    最快更新
    -0.31
    POSITIVE LOGITS
    LookAnd
    0.81
    OGND
    0.55
    ">//
    0.54
    GEBURTS
    0.54
    didSet
    0.53
    ManagedBean
    0.50
    mybatisplus
    0.50
    guigu
    0.49
    ArrowToggle
    0.49
     initComponents
    0.47
    Activations Density 0.005%

    No Known Activations