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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 11932
    Prev
    Next
    INDEX
    Explanations

    programming language constructs and class definitions

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

    Extends a class or implements an interface

    np_acts-logits-general · gemini-2.0-flash

    class inheritance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.69
    ImageContext
    -0.69
    Tikang
    -0.68
    IntoConstraints
    -0.67
    ParallelGroup
    -0.67
     ModelExpression
    -0.65
    WireFormatLite
    -0.65
    sizeCache
    -0.61
    AccessorTable
    -0.60
     MainAxisSize
    -0.60
    POSITIVE LOGITS
     base
    1.19
     Base
    1.14
    Base
    1.11
    Abstract
    1.04
    base
    1.04
     Abstract
    1.03
     abstract
    0.98
    abstract
    0.96
     bases
    0.86
     ABSTRACT
    0.86
    Activations Density 0.287%

    No Known Activations