© 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. 20-GEMMASCOPE-RES-16K
    6. 2655
    Prev
    Next
    INDEX
    Explanations

    phrases indicating confirmation or understanding

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

    phrases seeking confirmation or checking understanding, like "correct me if I'm wrong" or "if I understand correctly".

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MemoryWarning
    -0.45
    价比
    -0.36
    
    -0.36
    BeginContext
    -0.34
    étude
    -0.33
    inaison
    -0.33
     esfuer
    -0.33
     душе
    -0.32
     canali
    -0.32
    oform
    -0.32
    POSITIVE LOGITS
     متعلقه
    0.54
     tarko
    0.50
    ?
    
    0.50
    SourceChecksum
    0.49
     maksud
    0.46
    …?
    0.46
    osoba
    0.45
    ?」
    0.45
    ofür
    0.44
    Итак
    0.44
    Activations Density 0.179%

    No Known Activations