© 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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 9740
    Prev
    Next
    INDEX
    Explanations

    structures and syntax in programming, particularly related to memory and data manipulation

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

    C code: #define macros and struct definitions

    np_acts-logits-general · gemini-2.0-flash

    terror, vis spectra

    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
    . 
    -0.86
    ​.
    -0.64
    principalColumn
    -0.64
    adaptiveStyles
    -0.63
    (${
    -0.62
    $^\
    -0.61
     resourceCulture
    -0.61
    }$​
    -0.60
     ffilmiau
    -0.60
    × 
    -0.60
    POSITIVE LOGITS
     )
    0.77
     ,
    0.65
     متعلقه
    0.65
     F
    0.60
     V
    0.59
     L
    0.56
     FUNC
    0.55
     ;
    0.55
     }
    0.52
     ]
    0.52
    Activations Density 0.042%

    No Known Activations