© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5621
    Prev
    Next
    INDEX
    Explanations

    phrases indicating responsibility and expectations in relationships or narratives

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

    "it" followed by a verb or adjective

    np_acts-logits-general · gemini-2.0-flash

    make it

    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
    Weblinks
    -0.53
    cluye
    -0.52
    UnknownFields
    -0.50
     ostavi
    -0.50
     geblieben
    -0.50
     gehabt
    -0.49
    skog
    -0.49
     déri
    -0.48
     dibawa
    -0.48
     essendo
    -0.48
    POSITIVE LOGITS
     happen
    1.02
     seem
    1.00
     appear
    0.98
     feel
    0.94
     look
    0.90
    appear
    0.79
     palatable
    0.78
     accessible
    0.78
     into
    0.77
    happen
    0.77
    Activations Density 0.175%

    No Known Activations