© 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. 15166
    Prev
    Next
    INDEX
    Explanations

    phrases expressing uncertainty or predictions about future capabilities or actions

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

    Preceding "able" or related to ability

    np_acts-logits-general · gemini-2.0-flash

    being able to do something

    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
     kat
    -0.35
    छे
    -0.34
    iVar
    -0.34
    Requires
    -0.33
    ===
    -0.33
     String
    -0.33
     रु
    -0.32
     Kat
    -0.32
     rend
    -0.31
    ="'+
    -0.31
    POSITIVE LOGITS
     ability
    1.35
     able
    1.28
     Ability
    1.05
    Ability
    1.02
     قادر
    0.96
     pysty
    0.93
     Fähigkeit
    0.93
     kemampuan
    0.90
     capaz
    0.90
     mampu
    0.89
    Activations Density 0.391%

    No Known Activations