© 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. 8990
    Prev
    Next
    INDEX
    Explanations

    references to navigation and progress through challenges

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

    the phrase "made its/their way" or similar constructions describing movement or progression.

    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
    SOUNDBITE
    -0.38
     mourut
    -0.37
    ğraf
    -0.36
    actéristi
    -0.34
     tră
    -0.34
     creș
    -0.34
    탄
    -0.32
    бва
    -0.30
     ostavi
    -0.30
     uș
    -0.29
    POSITIVE LOGITS
     way
    1.15
     WAY
    0.92
    Way
    0.88
     Way
    0.85
    way
    0.79
    WAY
    0.76
     путь
    0.71
     طريق
    0.71
     camino
    0.67
     راه
    0.65
    Activations Density 0.151%

    No Known Activations