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. 82521
    Prev
    Next
    INDEX
    Explanations

    C++ mathematical library includes

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

    user

    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
    QtWidgets
    -0.45
     otomatig
    -0.44
    menuStrip
    -0.40
    LV
    -0.40
     manej
    -0.39
    setupUi
    -0.39
     useHistory
    -0.39
     empe
    -0.38
     spoilt
    -0.38
     vest
    -0.38
    POSITIVE LOGITS
    cmath
    4.19
    cstring
    0.84
    cstdlib
    0.82
    iomanip
    0.60
     '\\;'
    0.56
     للمعارف
    0.55
    cassert
    0.54
    pyplot
    0.53
    iostream
    0.52
    Tracce
    0.52
    Activations Density 0.000%

    No Known Activations