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. 24-GEMMASCOPE-RES-16K
    6. 5686
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and structures in code syntax

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

    Android UI elements/attributes

    np_acts-logits-general · gemini-2.0-flash

    android ui elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.65
    ImageContext
    -0.60
     فريبيس
    -0.52
    Tembelea
    -0.50
    providedIn
    -0.49
    BufferException
    -0.48
     createSlice
    -0.47
     resourceCulture
    -0.47
    MessageOf
    -0.46
    NameInMap
    -0.46
    POSITIVE LOGITS
    AttributeSet
    0.45
    WebControls
    0.44
     widget
    0.44
     montaż
    0.43
     addSubview
    0.43
     ddelweddau
    0.41
     initWithFrame
    0.40
    dflare
    0.40
     filhos
    0.39
     dipasang
    0.39
    Activations Density 0.641%

    No Known Activations