Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 1879
    Prev
    Next
    INDEX
    Explanations

    code import statements related to Java and its utility packages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     argint
    -0.45
     trasera
    -0.34
     Ketika
    -0.33
     когда
    -0.33
    <eos>
    -0.31
     اینکه
    -0.31
     espect
    -0.31
    kannt
    -0.31
    <bos>
    -0.30
     trust
    -0.30
    POSITIVE LOGITS
     java
    1.04
    abestanden
    0.78
    httphttps
    0.77
     javax
    0.74
     snippetHide
    0.73
     للاسماء
    0.73
    :+:
    0.69
    VersionUID
    0.69
     PhpStorm
    0.66
     <<<<<<<<<<<<<<
    0.65
    Activations Density 0.030%

    No Known Activations