© 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. 3-GEMMASCOPE-RES-16K
    6. 5675
    Prev
    Next
    INDEX
    Explanations

    phrases indicating auditing and quality assurance processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cha
    -0.36
     pla
    -0.35
     “
    -0.34
     Carlo
    -0.33
     specific
    -0.33
     Heiden
    -0.33
    ↵↵
    -0.32
     «
    -0.31
     bright
    -0.30
    ’
    -0.30
    POSITIVE LOGITS
     Normdatei
    0.81
    RectangleBorder
    0.66
    
    0.65
    Portail
    0.63
    ंदीखरीदारी
    0.62
    tanleria
    0.60
    الإنجليزية
    0.60
    ValueStyle
    0.59
    MLLoader
    0.58
    ReusableCell
    0.58
    Activations Density 2.242%

    No Known Activations