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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2451
    Prev
    Next
    INDEX
    Explanations

    conditional statements or phrases that introduce hypothetical scenarios

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

    even if

    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
     valueOf
    -0.47
    TemporalType
    -0.45
    WebVitals
    -0.40
     propOrder
    -0.39
    AddTagHelper
    -0.38
    ViewChild
    -0.37
     newUser
    -0.37
     voici
    -0.37
    AutoModerator
    -0.36
    verifyException
    -0.36
    POSITIVE LOGITS
    Though
    0.66
    though
    0.62
    ostante
    0.61
    尽管
    0.60
    Mesmo
    0.57
    Meskipun
    0.57
    就算
    0.57
     Though
    0.57
    Aunque
    0.56
    Despite
    0.56
    Activations Density 0.013%

    No Known Activations