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. 3402
    Prev
    Next
    INDEX
    Explanations

    components related to user interface buttons and their attributes in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    setViewportView
    -0.70
    帖最后由
    -0.66
    AddTagHelper
    -0.61
    transQ
    -0.53
     TimeUnit
    -0.52
    TypedDataSet
    -0.51
    OGND
    -0.51
    DataPropertyName
    -0.51
    EFIAPI
    -0.51
    ughty
    -0.51
    POSITIVE LOGITS
     botones
    0.35
     buttons
    0.33
     bouton
    0.32
     estri
    0.31
    WithIOException
    0.31
    pushButton
    0.30
    Button
    0.29
    ボタン
    0.28
    QPushButton
    0.28
     ProgressDialog
    0.27
    Activations Density 0.164%

    No Known Activations