© 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. 9-GEMMASCOPE-RES-131K
    6. 55665
    Prev
    Next
    INDEX
    Explanations

    comparative functions and assertions in code

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

    code equality checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Numerade
    -0.65
    tagHelperRunner
    -0.60
    AutoScaleMode
    -0.59
     ligiloj
    -0.59
     Савезне
    -0.55
     Administrativna
    -0.54
     Infórmanos
    -0.52
    AsUp
    -0.52
     nakalista
    -0.51
     tartalomajánló
    -0.51
    POSITIVE LOGITS
    assertEqual
    1.16
    assertEquals
    1.08
    assertSame
    0.95
    AreEqual
    0.78
    equal
    0.71
    XCTAssertEqual
    0.71
    willReturn
    0.61
    identical
    0.60
    eq
    0.59
     equal
    0.59
    Activations Density 0.002%

    No Known Activations