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 - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16073
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "be" in various forms and contexts

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

    Comes before an adjective describing a person

    np_acts-logits-general · gemini-2.0-flash

    be + quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.58
    Rüyada
    -0.53
    Datuak
    -0.49
    SourceChecksum
    -0.49
     ExecuteAsync
    -0.48
    IVEREF
    -0.46
    escaped
    -0.46
    CppMethod
    -0.45
    WebpackPlugin
    -0.45
    pushFollow
    -0.44
    POSITIVE LOGITS
     proactive
    0.62
     kasarigan
    0.47
     able
    0.47
     sure
    0.47
     flexible
    0.45
     honest
    0.45
     productive
    0.44
     creative
    0.43
     patient
    0.43
     part
    0.41
    Activations Density 0.152%

    No Known Activations