© 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. 10-GEMMASCOPE-RES-16K
    6. 1938
    Prev
    Next
    INDEX
    Explanations

    technical instructions related to project management and configuration setups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.79
    HasAnnotation
    -0.56
    LayoutStyle
    -0.54
    messageInfo
    -0.52
    httphttps
    -0.51
    WireFormatLite
    -0.50
    发表于
    -0.50
    gameserver
    -0.49
     AssemblyProduct
    -0.47
    ValueStyle
    -0.47
    POSITIVE LOGITS
     yourself
    0.73
    qrstuvwxyz
    0.68
     aikaa
    0.60
    WriteTagHelper
    0.56
     customizations
    0.55
    salvar
    0.55
    UrlResolution
    0.54
     väli
    0.54
     quelconque
    0.54
    WebElementEntity
    0.54
    Activations Density 0.577%

    No Known Activations