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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 8264
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and terminology related to functions, estimates, and statistical properties

    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
    ClientRect
    -0.69
    RTEX
    -0.65
    IntoConstraints
    -0.63
    PreferredItem
    -0.63
    MethodManager
    -0.60
     MotionEvent
    -0.56
    ChildScrollView
    -0.54
    DockStyle
    -0.54
    addContainerGap
    -0.54
    xrLabel
    -0.53
    POSITIVE LOGITS
    fjspx
    0.74
    ActionCreators
    0.63
    FormTagHelper
    0.58
    ఔ
    0.41
    MenuInflater
    0.41
    Према
    0.40
    MLLoader
    0.39
    CompleteListener
    0.39
    Scénario
    0.39
    生平
    0.38
    Activations Density 2.266%

    No Known Activations