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. 302
    Prev
    Next
    INDEX
    Explanations

    references to various types and species of beetles

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

    beetle, beetles, Beatles, Beetlejuice, Beetle Bailey

    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
     surla
    -0.79
    曖昧さ回避
    -0.67
    ✨:
    -0.65
    OGND
    -0.60
     utafitiHapana
    -0.60
     ICF
    -0.59
     Soriano
    -0.56
     Rar
    -0.56
     GenerationType
    -0.54
    __*/
    -0.54
    POSITIVE LOGITS
     beetle
    2.03
     Beetle
    1.97
     beetles
    1.89
     Beet
    1.28
    etle
    1.03
    beet
    0.94
     insect
    0.79
     insecto
    0.74
     bug
    0.73
     insectos
    0.73
    Activations Density 0.005%

    No Known Activations