Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 38597
    Prev
    Next
    INDEX
    Explanations

    trigonometric functions and their variations

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

    mathematical sine expressions

    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
     kasarigan
    -0.51
     utafitiHapana
    -0.51
    jenigen
    -0.50
    EFIAPI
    -0.50
    Personendaten
    -0.49
    ท่าน
    -0.47
     quelli
    -0.47
     solches
    -0.46
    antaranya
    -0.46
    others
    -0.44
    POSITIVE LOGITS
    sin
    1.38
     sin
    1.24
     Sin
    0.91
    Sin
    0.88
    cos
    0.78
     Sine
    0.77
     SIN
    0.73
    sinh
    0.73
    sinx
    0.72
    Sine
    0.71
    Activations Density 0.045%

    No Known Activations