© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 38524
    Prev
    Next
    INDEX
    Explanations

    mentions of the Django framework and related components

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

    django and odoo frameworks

    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
     better
    -0.34
     being
    -0.32
     comigo
    -0.31
     huom
    -0.30
     means
    -0.29
     paire
    -0.29
    ↵↵
    -0.28
    no
    -0.28
     réessayer
    -0.28
     having
    -0.27
    POSITIVE LOGITS
     django
    1.02
    IUrlHelper
    0.99
    IntoConstraints
    0.81
    TypedDataSet
    0.80
     ModelExpression
    0.79
    BASEPATH
    0.79
    CppMethod
    0.79
     ब्रेकडाउन
    0.77
    Vidite
    0.76
     témoig
    0.75
    Activations Density 0.001%

    No Known Activations