© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 2600
    Prev
    Next
    INDEX
    Explanations

    references to racing incidents or crashes

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

    descriptions of vehicles navigating challenging road conditions or corners at high speed.

    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
     betweenstory
    -0.42
     تضيفلها
    -0.38
    InternalFrame
    -0.34
    jednoc
    -0.32
     SPDX
    -0.31
     aapt
    -0.31
    transQ
    -0.31
    Weblinks
    -0.30
     halk
    -0.30
    っこう
    -0.30
    POSITIVE LOGITS
     bends
    1.22
     curve
    1.17
     curves
    1.16
     bend
    1.16
     turn
    1.15
     turns
    1.13
    Turn
    1.09
     Turn
    1.08
    turn
    1.08
    turns
    1.04
    Activations Density 0.214%

    No Known Activations