Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5056
    Prev
    Next
    INDEX
    Explanations

    structured programming commands and assignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -0.67
    EndContext
    -0.62
    ISupport
    -0.58
    󠁢
    -0.56
     nader
    -0.56
    脚注の使い方
    -0.55
    MessageTagHelper
    -0.54
    ParallelGroup
    -0.54
    iibo
    -0.54
    ViewImports
    -0.54
    POSITIVE LOGITS
     Erscheinung
    0.40
     cerdo
    0.37
     plegable
    0.37
     normalidad
    0.36
     roulant
    0.34
    bitset
    0.34
    prefixer
    0.34
    devtool
    0.33
     taş
    0.33
     compreensão
    0.32
    Activations Density 0.418%

    No Known Activations