© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 8637
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential challenges or difficulties in various contexts

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

    "can" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    can followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Likely
    -0.51
    Likely
    -0.49
    Probably
    -0.49
    presumably
    -0.48
     probably
    -0.47
    probably
    -0.47
    必然
    -0.47
     Probably
    -0.47
     provavelmente
    -0.46
    likely
    -0.46
    POSITIVE LOGITS
     akár
    0.78
     бывают
    0.75
     бывает
    0.73
     sometimes
    0.66
     canst
    0.65
     durchaus
    0.63
     ibland
    0.57
     parfois
    0.57
     fometimes
    0.56
    sometimes
    0.54
    Activations Density 0.426%

    No Known Activations