© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 4781
    Prev
    Next
    INDEX
    Explanations

    Java programming keywords and structure in code snippets

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

    open parentheses in code syntax, particularly those following method/function names and type declarations.

    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
    DockStyle
    -0.53
     &___
    -0.52
    Бахар
    -0.48
    ANTLR
    -0.44
    AddHtmlAttribute
    -0.44
    OrNil
    -0.43
     Händen
    -0.42
    ftagPool
    -0.42
    AndEndTag
    -0.42
    jenigen
    -0.41
    POSITIVE LOGITS
     Branch
    0.63
     Row
    0.60
     Cell
    0.60
     Group
    0.58
     Point
    0.58
     Person
    0.55
     Field
    0.55
     Lane
    0.54
     Port
    0.54
     Song
    0.54
    Activations Density 0.959%

    No Known Activations