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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 113801
    Prev
    Next
    INDEX
    Explanations

    terminology related to programming concepts, specifically regarding accessors, constructors, and method definitions

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

    getters, setters, and constructors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    zbęd
    -0.44
     tranſ
    -0.43
    (!__
    -0.40
     viewDidLoad
    -0.40
    postDelayed
    -0.40
    ClientSize
    -0.36
    PYX
    -0.35
     Chriſt
    -0.34
    ppuden
    -0.34
     Queen
    -0.34
    POSITIVE LOGITS
    classmethod
    0.54
    BagLayout
    0.54
     MainAxisSize
    0.54
    itzender
    0.52
    staticmethod
    0.48
     متعلقه
    0.47
     desmotivaciones
    0.47
    batore
    0.46
     AttributeSet
    0.45
    日閲覧
    0.45
    Activations Density 0.054%

    No Known Activations