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

    Neuronpedia

    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. 22-GEMMASCOPE-RES-16K
    11. 8643
    Prev
    Next
    INDEX
    Explanations

    questions related to capability and possibility, especially those framed as "how can" inquiries

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

    Tokens followed by questions

    np_acts-logits-general · gemini-2.0-flash

    auxiliary verb question starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bewerken
    -0.69
     zwar
    -0.69
     gimana
    -0.69
    MLLoader
    -0.69
    ſelves
    -0.68
     незавершена
    -0.68
    OGND
    -0.68
     Ause
    -0.67
    ſelf
    -0.66
    सन्दर्भ
    -0.66
    POSITIVE LOGITS
     we
    1.04
     they
    0.96
     you
    0.82
     he
    0.74
     the
    0.71
    RetentionPolicy
    0.70
     these
    0.70
     I
    0.60
     people
    0.59
     she
    0.55
    Activations Density 0.170%

    No Known Activations