© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 8407
    Prev
    Next
    INDEX
    Explanations

    class inheritance and framework-based object-oriented design patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.88
    GEBURTSDATUM
    -0.84
     للاسماء
    -0.70
    RotationOrder
    -0.69
    MLLoader
    -0.67
     فريبيس
    -0.66
    sizeCache
    -0.63
    UnusedPrivate
    -0.63
    ConstraintMaker
    -0.61
    WireFormatLite
    -0.59
    POSITIVE LOGITS
     base
    1.04
     Base
    1.02
    Base
    0.98
     Abstract
    0.93
    Abstract
    0.92
    base
    0.89
     abstract
    0.88
    abstract
    0.83
     bases
    0.73
     ABSTRACT
    0.73
    Activations Density 0.165%

    No Known Activations