© 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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 15981
    Prev
    Next
    INDEX
    Explanations

    various data structure keywords and generic type declarations in code

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

    Code-related terms and symbols

    np_acts-logits-general · gemini-2.0-flash

    code constructs and generics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    DockStyle
    -0.83
     ]
    
    -0.75
     [],
    
    -0.70
     ...]
    -0.68
    !]
    -0.67
     [];
    
    -0.66
     "];
    -0.64
    "]),
    -0.62
     "]
    -0.62
     ")
    
    -0.62
    POSITIVE LOGITS
    <
    0.81
    <?
    0.65
    <?>
    0.64
    <_
    0.56
    KommentareTeilen
    0.49
    <!--
    0.48
     unknownFields
    0.48
     uVar
    0.47
    jning
    0.47
    estrian
    0.46
    Activations Density 0.065%

    No Known Activations