© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104809
    Prev
    Next
    INDEX
    Explanations

    code-related commands and functions, particularly those involving input/output operations

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

    C++ input operations

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     CreateTagHelper
    -0.35
     Favor
    -0.35
     affich
    -0.35
    iterate
    -0.34
     extinct
    -0.34
     Aus
    -0.34
    ectors
    -0.34
     trit
    -0.34
    ateur
    -0.33
     đá
    -0.33
    POSITIVE LOGITS
    MethodManager
    0.79
    +#+
    0.69
     المعيارى
    0.68
    ंदीखरीदारी
    0.67
    twimg
    0.64
     Мексичка
    0.57
    HtmlAttribute
    0.57
    TemporalType
    0.56
    Personendaten
    0.56
    FieldBuilder
    0.54
    Activations Density 0.008%

    No Known Activations