© 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. 6700
    Prev
    Next
    INDEX
    Explanations

    patterns related to network protocols and data structure elements

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

    low-level system or network protocol flags and configuration parameters.

    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
     jadx
    -0.40
    AutoField
    -0.35
    epam
    -0.30
     اف
    -0.30
    #+#
    -0.30
    Sos
    -0.29
    EClass
    -0.28
     mas
    -0.28
     Sos
    -0.28
     برانيه
    -0.28
    POSITIVE LOGITS
     nahilalakip
    0.67
    دانشنامهٔ
    0.56
     stanga
    0.52
    ngdoc
    0.50
     <=",
    0.48
    
    0.48
    mapStateToProps
    0.48
    SerializedName
    0.47
     noDo
    0.46
    AutoScaleMode
    0.46
    Activations Density 0.171%

    No Known Activations