© 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. 8811
    Prev
    Next
    INDEX
    Explanations

    terms related to practical applications or practices in various contexts

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

    the word "practice" in professional and academic contexts.

    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
    ennemi
    -0.33
    ulisan
    -0.32
     Zem
    -0.32
     Muro
    -0.31
     Bea
    -0.31
     presa
    -0.29
    édric
    -0.28
     Goddess
    -0.28
     lighting
    -0.28
     birra
    -0.27
    POSITIVE LOGITS
    Practice
    0.76
     Practice
    0.76
    Practi
    0.74
    RTCF
    0.72
    PRACTICE
    0.71
     للاسماء
    0.69
     HasFactory
    0.69
     Practi
    0.66
    parsedMessage
    0.66
    principalColumn
    0.65
    Activations Density 0.199%

    No Known Activations