© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4040
    Prev
    Next
    INDEX
    Explanations

    empty or whitespace substrings in code or text blocks

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

    Code keywords and control flow statements

    np_acts-logits-general · gemini-2.0-flash

    conditional `if` and `for`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -1.04
     cherchés
    -0.92
     tartalomajánló
    -0.89
    SBATCH
    -0.89
     onAnimation
    -0.87
    Бахар
    -0.87
    CloseOperation
    -0.86
     StatelessWidget
    -0.85
     BoxFit
    -0.84
    tvguidetime
    -0.84
    POSITIVE LOGITS
    if
    0.93
    ↵↵
    0.81
    ↵
    0.71
    for
    0.70
     
    0.70
    <eos>
    0.64
    //
    0.60
    0.59
     I
    0.58
     if
    0.55
    Activations Density 0.116%
    No Known Activations