Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 8448
    Prev
    Next
    INDEX
    Explanations

    phrases and indicators related to code generation and editing constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    providedIn
    -0.93
    GenerationType
    -0.87
    IntoConstraints
    -0.82
     HttpNotFound
    -0.75
    ftagPool
    -0.74
     оригіналу
    -0.72
     BoxFit
    -0.71
    sizeCache
    -0.71
     NSCoder
    -0.70
    BASEPATH
    -0.70
    POSITIVE LOGITS
    DebuggerNonUser
    0.28
     step
    0.26
    step
    0.25
     VIAF
    0.25
    DISABLE
    0.23
     محل
    0.23
    generated
    0.23
    mstyle
    0.23
    surf
    0.22
    ımız
    0.22
    Activations Density 0.450%

    No Known Activations