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. 9-GEMMASCOPE-RES-16K
    6. 3731
    Prev
    Next
    INDEX
    Explanations

    paths and parameters related to API requests

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

    Code paths or URLs

    np_acts-logits-general · gemini-2.0-flash

    network endpoints and paths

    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
     StatelessWidget
    -0.73
     kasarigan
    -0.67
    sizeCache
    -0.57
     zijne
    -0.49
     StatefulWidget
    -0.49
     nonUne
    -0.48
     tartalomajánló
    -0.48
    AsUp
    -0.47
    WebElementEntity
    -0.46
    jspb
    -0.44
    POSITIVE LOGITS
    RequestParam
    1.52
    PathVariable
    1.41
    ("/
    1.01
    ('/
    0.99
    localhost
    0.74
    RequestBody
    0.73
    PathParam
    0.70
    ="/
    0.66
    Param
    0.65
    ("/:
    0.64
    Activations Density 0.061%

    No Known Activations