© 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. 6086
    Prev
    Next
    INDEX
    Explanations

    terms related to personal actions or questions

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

    Following "you," "I," or "it" and preceding "can" or "could"

    np_acts-logits-general · gemini-2.0-flash

    pronoun can

    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
    EndInit
    -0.57
    twimg
    -0.56
    pides
    -0.54
     Exacts
    -0.53
     INTERESAR
    -0.52
    ResumeLayout
    -0.49
    UALA
    -0.48
    interopRequire
    -0.48
    rawDesc
    -0.48
     kaynağından
    -0.47
    POSITIVE LOGITS
     can
    3.68
    can
    2.69
    Can
    2.44
     Can
    2.36
     could
    2.05
     dapat
    2.02
     kann
    1.99
     CAN
    1.99
     können
    1.98
     bisa
    1.97
    Activations Density 1.564%

    No Known Activations