Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 29396
    Prev
    Next
    INDEX
    Explanations

    keywords related to environmental conservation and wildlife protection

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

    critically endangered species

    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
    ,
    -0.44
     Económica
    -0.41
     (
    -0.39
     bahía
    -0.37
    月号
    -0.35
     coute
    -0.35
     bahç
    -0.34
    vemos
    -0.34
     however
    -0.33
     our
    -0.33
    POSITIVE LOGITS
    :✨
    0.68
    Autoritní
    0.61
    rungsseite
    0.60
    RegressionTest
    0.58
    DockStyle
    0.54
    __':
    0.54
    __":
    0.54
     Roskov
    0.53
     CanadaChoose
    0.51
     kasarigan
    0.50
    Activations Density 0.134%

    No Known Activations