© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2831
    Prev
    Next
    INDEX
    Explanations

    specific combinations of character sequences and variable names in programming code

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

    code and technical documentation details, especially related to data analysis and programming syntax.

    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
    TargetException
    -0.45
     cir
    -0.43
     innovation
    -0.41
    sound
    -0.40
     Cir
    -0.40
     cial
    -0.40
     sound
    -0.40
    
    -0.40
     Santos
    -0.40
     CIR
    -0.39
    POSITIVE LOGITS
    AlterField
    0.55
    Autoritní
    0.47
     surla
    0.47
    verwijspagina
    0.47
    principalColumn
    0.46
     GenerationType
    0.45
    期刊论文
    0.43
    ≦)
    0.42
    LookAnd
    0.42
     heisst
    0.42
    Activations Density 0.367%

    No Known Activations