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

    Neuronpedia

    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. 31-GEMMASCOPE-RES-16K
    11. 4667
    Prev
    Next
    INDEX
    Explanations

    occurrences of null or zero values in programming contexts

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

    numeric literal zero values in code assignments and initializations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HomeAsUpEnabled
    -0.53
     فريبيس
    -0.44
    Portail
    -0.44
    (!__
    -0.43
    webElement
    -0.42
     Straight
    -0.41
    Hauptartikel
    -0.41
    ugc
    -0.41
     ब्रेकडाउन
    -0.40
    Życiorys
    -0.39
    POSITIVE LOGITS
    IntoConstraints
    0.58
    +#+#
    0.50
     estekak
    0.50
    yntaxException
    0.48
     wireType
    0.48
    FormTagHelper
    0.46
     EClass
    0.45
     geweest
    0.42
    ConstraintMaker
    0.36
    oredCriteria
    0.36
    Activations Density 0.213%

    No Known Activations