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. 34-GEMMASCOPE-RES-16K
    6. 10923
    Prev
    Next
    INDEX
    Explanations

    numerical values related to ranges and thresholds in scientific measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTEX
    -0.43
     informée
    -0.36
    évaluateur
    -0.36
     thiệu
    -0.35
    tomation
    -0.34
    Personensuche
    -0.33
     GlobalKey
    -0.33
    enschappelijke
    -0.33
    oplayer
    -0.33
     ComVisible
    -0.32
    POSITIVE LOGITS
     range
    3.20
    range
    2.67
     ranges
    2.66
     Range
    2.64
    Range
    2.53
     RANGE
    2.52
    RANGE
    2.23
     Ranges
    2.23
    ranges
    2.09
    Ranges
    2.05
    Activations Density 1.395%

    No Known Activations