© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 583
    Prev
    Next
    INDEX
    Explanations

    programming-related errors and conditions in code

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

    Errors in request preparation or sending

    np_acts-logits-general · gemini-2.0-flash

    checking for errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    AsUp
    -0.56
    ControllerAdvice
    -0.52
    BASEPATH
    -0.51
     سكانية
    -0.50
     Sonn
    -0.49
    transQ
    -0.48
    Precalculus
    -0.48
    ፩
    -0.47
    DataPropertyName
    -0.47
     nonUne
    -0.47
    POSITIVE LOGITS
    MessageTagHelper
    0.59
     nakalista
    0.57
    NSError
    0.52
    ViewFeatures
    0.41
    wantErr
    0.40
     NSError
    0.39
    printStackTrace
    0.39
     err
    0.38
    Worse
    0.38
    OCCURRED
    0.37
    Activations Density 0.060%

    No Known Activations