© 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. 24-GEMMASCOPE-RES-16K
    6. 1838
    Prev
    Next
    INDEX
    Explanations

    programming and file-related keywords or identifiers

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

    Code-related tokens followed by delimiters

    np_acts-logits-general · gemini-2.0-flash

    identifiers and string literals

    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
    tagHelperRunner
    -0.83
    ValueStyle
    -0.82
     Chwiliwch
    -0.78
    rungsseite
    -0.77
     CreateTagHelper
    -0.76
    AndEndTag
    -0.70
    SourceChecksum
    -0.69
     otomatig
    -0.65
    ########.
    -0.65
    >--}}
    -0.65
    POSITIVE LOGITS
    ”
    0.66
    ",
    0.61
    」
    0.60
    "
    0.59
    ”,
    0.54
    ".
    0.53
    ”.
    0.52
    "
    
    0.48
    ";
    0.48
    ")
    0.46
    Activations Density 1.486%

    No Known Activations