© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 3128
    Prev
    Next
    INDEX
    Explanations

    references to programming elements, particularly those related to user interface components and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arşivlendi
    -0.59
     مشين
    -0.49
    ſhip
    -0.49
     Majefty
    -0.48
    ReusableCell
    -0.47
     onPostExecute
    -0.46
    ſelf
    -0.44
    interpr
    -0.44
     husk
    -0.43
     vastaan
    -0.43
    POSITIVE LOGITS
    TagHelper
    0.49
    SequentialGroup
    0.47
    XmlType
    0.44
     쿠
    0.43
     }}">
    0.43
    fxml
    0.43
     mouseY
    0.43
    TextField
    0.43
    EditText
    0.41
     client
    0.41
    Activations Density 1.880%

    No Known Activations