Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 9227
    Prev
    Next
    INDEX
    Explanations

    key phrases related to advancement and performance in various contexts

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

    phrases describing escalation or reaching a higher level of intensity or achievement.

    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
    OGND
    -0.37
    posedge
    -0.37
     kasarigan
    -0.36
    parsedMessage
    -0.32
    wnież
    -0.30
    Sucesor
    -0.30
    pushFollow
    -0.30
    
    -0.30
    брь
    -0.30
    κολου
    -0.30
    POSITIVE LOGITS
     level
    0.93
    level
    0.85
     levels
    0.81
    レベル
    0.80
     next
    0.77
     elevate
    0.75
     nivå
    0.73
     nivelul
    0.71
    Level
    0.70
     elevated
    0.70
    Activations Density 0.111%

    No Known Activations