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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5896
    Prev
    Next
    INDEX
    Explanations

    keywords related to boolean return values and control flow in programming

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

    Code indicating success or boolean values

    np_acts-logits-general · gemini-2.0-flash

    success or failure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snippetHide
    -0.69
     الحره
    -0.62
     يتيمه
    -0.61
     EdgeInsets
    -0.56
    AndEndTag
    -0.55
    Autoritní
    -0.50
    getStringExtra
    -0.49
    tanleria
    -0.49
     ویکی‌پدیا
    -0.49
    OGND
    -0.47
    POSITIVE LOGITS
     réuss
    0.47
     réus
    0.45
     성공
    0.45
    成功
    0.44
     réussir
    0.40
     réussi
    0.39
     succeeded
    0.38
     úspě
    0.37
    baiki
    0.37
    否
    0.37
    Activations Density 0.265%

    No Known Activations