© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15504
    Prev
    Next
    INDEX
    Explanations

    C++ programming constructs and syntax related to input and output operations

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

    C++ code, including "<<" and "cout"

    np_acts-logits-general · gemini-2.0-flash

    C++ stream output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    delete
    -0.90
    free
    -0.86
    ItemBackground
    -0.81
     freeing
    -0.78
     free
    -0.78
    Free
    -0.74
     frees
    -0.72
     Free
    -0.71
     liberated
    -0.70
     delete
    -0.70
    POSITIVE LOGITS
    Sklici
    0.48
    Captor
    0.47
    NSIndexPath
    0.44
    iose
    0.42
    >>
    0.42
    Linki
    0.42
    ובה
    0.41
    脚注の使い方
    0.41
    ïsme
    0.41
    ISME
    0.41
    Activations Density 0.169%

    No Known Activations