© 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. 9-GEMMASCOPE-RES-131K
    11. 34884
    Prev
    Next
    INDEX
    Explanations

    terms related to infrastructure and physical structures

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

    freeway, precinct, fastening

    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
    qü
    -0.47
    Xor
    -0.43
     Jurí
    -0.40
    Suk
    -0.39
    ésult
    -0.39
    ficulty
    -0.39
     hx
    -0.38
     longa
    -0.38
    ByID
    -0.38
    niosek
    -0.38
    POSITIVE LOGITS
     pavement
    1.66
     Pavement
    1.51
     pavements
    1.34
     pavimento
    0.77
    vement
    0.76
    PackageManager
    0.68
    bourhood
    0.66
     Pave
    0.65
     PackageManager
    0.63
    ########.
    0.63
    Activations Density 0.007%

    No Known Activations