© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4806
    Prev
    Next
    INDEX
    Explanations

    specific names and significant terms related to vessels or maritime contexts

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

    city names in geographical contexts.

    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
     nahilalakip
    -0.54
    tvguidetime
    -0.50
     للمعارف
    -0.41
    etheless
    -0.40
    getInventory
    -0.38
     praktijk
    -0.37
     sprend
    -0.36
     entails
    -0.36
     betreft
    -0.36
    寂寞
    -0.36
    POSITIVE LOGITS
    Tempo
    0.42
    saraba
    0.41
    InitVars
    0.41
     прош
    0.41
    umumkan
    0.41
    leyeb
    0.40
    covo
    0.40
     Anſ
    0.39
     rootReducer
    0.39
     setUsername
    0.38
    Activations Density 0.224%

    No Known Activations