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. 61628
    Prev
    Next
    INDEX
    Explanations

    accounts of accidents and injuries

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

    killed himself when

    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
    ValueStyle
    -0.77
     ProtoMessage
    -0.55
    windowFixed
    -0.44
    醐
    -0.41
    udessa
    -0.40
    testens
    -0.38
    İstinadlar
    -0.37
    Cyfeiriadau
    -0.37
    ierto
    -0.35
    +#+#
    -0.35
    POSITIVE LOGITS
     InputDecoration
    0.52
    XtraReports
    0.52
    Personendaten
    0.50
    abetes
    0.45
     inputStream
    0.44
     detained
    0.44
    舺
    0.44
     Ngb
    0.43
     sentenced
    0.42
    revenge
    0.41
    Activations Density 0.049%

    No Known Activations