© 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. 3449
    Prev
    Next
    INDEX
    Explanations

    code-related components, particularly in a GUI context

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

    Java programming code syntax and method calls.

    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
    AddTagHelper
    -0.79
    mybatisplus
    -0.67
     noDo
    -0.61
     Administrativna
    -0.56
    -------
    -0.56
     censiti
    -0.55
    Билгалдахарш
    -0.55
    OCCURRED
    -0.53
    jsonwebtoken
    -0.52
    OGND
    -0.52
    POSITIVE LOGITS
     selection
    0.42
     selections
    0.37
     interface
    0.35
     Selection
    0.35
     series
    0.34
     Inspection
    0.34
     results
    0.34
     frontale
    0.34
     following
    0.34
     Interface
    0.32
    Activations Density 0.081%

    No Known Activations