© 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. 9620
    Prev
    Next
    INDEX
    Explanations

    phrases related to movement and transitions

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

    phrases indicating the continuation or progression of actions or narratives using "from there" or similar transitional structures.

    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
     calendriers
    -0.43
    
    -0.43
    ValueStyle
    -0.42
    getColumnIndex
    -0.41
    theoremstyle
    -0.40
    glises
    -0.40
    TextWatcher
    -0.39
    исленность
    -0.38
    RTEE
    -0.38
    RectangleBorder
    -0.37
    POSITIVE LOGITS
     там
    2.27
     allí
    2.19
     dort
    2.08
     therein
    2.03
    在那里
    1.98
     acolo
    1.89
     آنجا
    1.84
    那里
    1.77
    Там
    1.77
     there
    1.75
    Activations Density 1.250%

    No Known Activations