© 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. 28-GEMMASCOPE-RES-16K
    11. 4495
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and method/function calls in code snippets

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

    Code snippets using functions like substr, equals, count

    np_acts-logits-general · gemini-2.0-flash

    string emptiness checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    期刊论文
    -0.56
     Theſe
    -0.51
    évaluateur
    -0.44
    WriteByte
    -0.42
     Reſ
    -0.39
     Diſ
    -0.36
     Inſ
    -0.36
    的说道
    -0.36
    原始内容存档
    -0.35
    zerű
    -0.35
    POSITIVE LOGITS
    rawDesc
    0.58
    MessageOf
    0.58
    IGraphics
    0.53
    CppMethod
    0.53
    IsMutable
    0.52
    LLocation
    0.51
    erapeutics
    0.50
    RepeatedField
    0.50
    ruptedException
    0.49
    omitempty
    0.49
    Activations Density 0.195%

    No Known Activations