© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 117784
    Prev
    Next
    INDEX
    Explanations

    variations of the word "munch" and related terms in different contexts

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

    stanchion, linchpin, bicinchoninic

    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
     erwartet
    -0.40
    __":
    -0.39
    '|
    -0.38
    assertNotNull
    -0.35
    verwijspagina
    -0.35
     ISNI
    -0.35
    новништво
    -0.34
    isArray
    -0.33
    Portale
    -0.33
    ®:
    -0.31
    POSITIVE LOGITS
    unch
    2.33
    UNCH
    1.77
    unched
    1.45
    uncher
    1.41
    unches
    1.39
     Munch
    1.30
    runch
    1.22
     munch
    1.06
    lunch
    1.02
    Lunch
    1.00
    Activations Density 0.009%

    No Known Activations