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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3300
    Prev
    Next
    INDEX
    Explanations

    structured data related to weather station datasets

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

    NOAA climate data or related functions

    np_acts-logits-general · gemini-2.0-flash

    NCDC stations and records

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -------------</
    -0.62
     betweenstory
    -0.62
    ReusableCell
    -0.52
     IBOutlet
    -0.49
    edicated
    -0.48
     pendek
    -0.47
    balleur
    -0.47
     bordir
    -0.47
    pushFollow
    -0.47
     TAMBÉM
    -0.46
    POSITIVE LOGITS
     AppCompatTheme
    0.43
    jstor
    0.40
    omburg
    0.39
    ClientRect
    0.36
     NCP
    0.35
     Mercu
    0.35
     nest
    0.35
     codex
    0.35
    länd
    0.35
    Visa
    0.35
    Activations Density 0.144%

    No Known Activations