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. 20-GEMMASCOPE-RES-131K
    6. 35721
    Prev
    Next
    INDEX
    Explanations

    references to camping and campgrounds

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

    various types of camps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    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>
    -0.49
     Wiener
    -0.42
    er
    -0.41
    bersicht
    -0.41
     שוליים
    -0.41
     UserDetails
    -0.40
     Neder
    -0.39
     Deus
    -0.38
     Reuter
    -0.38
     indisponible
    -0.38
    POSITIVE LOGITS
     camp
    1.30
     Camp
    1.23
    Camp
    1.19
     camps
    1.17
    camp
    1.11
     Camps
    1.09
     CAMP
    1.09
     campamento
    1.02
    CAMP
    1.00
     campers
    0.96
    Activations Density 0.006%

    No Known Activations