© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 3887
    Prev
    Next
    INDEX
    Explanations

    code-related structure and flow elements, particularly function definitions and control structures

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

    Python code blocks with "with" statements

    np_acts-logits-general · gemini-2.0-flash

    `with ... as` CLI commands

    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
    出版年
    -0.42
    
    -0.42
    ">//
    -0.42
    ⇡
    -0.39
     يتيمه
    -0.39
    ONOMY
    -0.38
     :)</
    -0.38
     stiefel
    -0.37
    ApiOperation
    -0.37
     ſte
    -0.36
    POSITIVE LOGITS
     AssemblyCulture
    0.66
    httphttps
    0.54
     pass
    0.52
     kasarigan
    0.51
    
    0.49
    MLLoader
    0.48
    couz
    0.45
     ویکی‌آمباردا
    0.44
    PyExc
    0.43
    ayuno
    0.42
    Activations Density 0.138%

    No Known Activations