© 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 - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 2801
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code and technical documentation with programming language syntax and output.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorTagHelper
    -0.36
     Administrativna
    -0.33
    стракт
    -0.33
    DataPropertyName
    -0.33
     disambiguazione
    -0.32
     Grüsse
    -0.32
     Sorge
    -0.31
    jeev
    -0.31
    uudet
    -0.31
    aronne
    -0.31
    POSITIVE LOGITS
     prompt
    1.11
    prompt
    1.00
     prompts
    0.95
     interactive
    0.94
     input
    0.93
     interac
    0.91
    Prompt
    0.90
     prompting
    0.88
     Prompt
    0.88
     Interactive
    0.82
    Activations Density 0.343%

    No Known Activations