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. 6905
    Prev
    Next
    INDEX
    Explanations

    specific college football teams and their performance statistics

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

    Followed by "University" or "State"

    np_acts-logits-general · gemini-2.0-flash

    university names

    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
    tonode
    -0.49
    Бахар
    -0.44
    RectangleBorder
    -0.44
    IntoConstraints
    -0.44
    getMinutes
    -0.44
    encji
    -0.41
    +#+#
    -0.41
     AspNetCore
    -0.41
     podí
    -0.41
    Baden
    -0.40
    POSITIVE LOGITS
     Administrativna
    0.82
     endregion
    0.42
     State
    0.40
    AddTagHelper
    0.39
    featureID
    0.37
    kosh
    0.37
    MENAFN
    0.37
    BitmapFactory
    0.36
    ########.
    0.35
    ResourceBundle
    0.35
    Activations Density 0.269%

    No Known Activations