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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 70381
    Prev
    Next
    INDEX
    Explanations

    terms related to computation and computer science

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

    computation

    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
    <bos>
    -0.67
    Vedi
    -0.50
    <h2>
    -0.40
    r
    -0.40
    hal
    -0.38
    Upper
    -0.38
     Els
    -0.38
    Cyl
    -0.38
    Els
    -0.37
     Liz
    -0.37
    POSITIVE LOGITS
     Computation
    1.77
     computation
    1.71
    Computation
    1.60
    computation
    1.49
     computations
    1.08
    compute
    0.74
     computed
    0.73
     COMPUT
    0.72
    ſelf
    0.71
    StoryboardSegue
    0.68
    Activations Density 0.007%

    No Known Activations