© 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. 107445
    Prev
    Next
    INDEX
    Explanations

    instances of the word "foo" and variations of it in different contexts and formats

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

    'foo' as identifier or string literal

    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
    fjspx
    -0.49
    .],
    -0.49
     Infórmanos
    -0.47
    erover
    -0.45
    "];
    -0.45
    ")));
    -0.44
    دانشنامهٔ
    -0.44
    uxxxx
    -0.43
     EKG
    -0.42
     PyLong
    -0.42
    POSITIVE LOGITS
    Foo
    1.08
     Foo
    1.03
    foo
    0.96
    FOO
    0.94
     foo
    0.86
     Foote
    0.78
    foobar
    0.70
     foodie
    0.67
     FOOD
    0.62
    脚注の使い方
    0.61
    Activations Density 0.011%

    No Known Activations