© 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. 14453
    Prev
    Next
    INDEX
    Explanations

    names and proper nouns, particularly related to individuals and academia

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

    before Hungarian names/titles

    np_acts-logits-general · gemini-2.0-flash

    names, specific terms

    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
     ProtoMessage
    -0.65
    }>;
    -0.61
    
    -0.56
    /*
    -0.54
    )))));
    -0.52
    [].
    -0.51
    GOTREF
    -0.51
     onCreateView
    -0.50
     {?>
    -0.49
    ]--;
    -0.49
    POSITIVE LOGITS
     kolo
    0.52
    SourceChecksum
    0.50
     Herce
    0.49
     télévisée
    0.47
     Lel
    0.47
     Test
    0.46
    Test
    0.46
     himo
    0.45
    morphic
    0.44
     öz
    0.43
    Activations Density 0.058%

    No Known Activations