© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 13024
    Prev
    Next
    INDEX
    Explanations

    terms related to file paths and directory structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 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
     myſelf
    -1.19
     ſmall
    -1.19
     Efq
    -1.17
     Monfieur
    -1.17
     Theſe
    -1.17
     pleaſure
    -1.12
     Jefus
    -1.12
     itſelf
    -1.11
     reaſon
    -1.10
     ſeveral
    -1.09
    POSITIVE LOGITS
     Path
    1.57
     PATH
    1.52
     path
    1.50
     paths
    1.45
    path
    1.42
     Paths
    1.40
    Path
    1.39
    PATH
    1.38
    paths
    1.38
     getPath
    1.24
    Activations Density 0.073%

    No Known Activations