© 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. 22-GEMMASCOPE-RES-16K
    11. 590
    Prev
    Next
    INDEX
    Explanations

    phrases indicating political actions or decisions

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

    following commas

    np_acts-logits-general · gemini-2.0-flash

    listing examples of conditions or specifications

    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
     –
    -0.60
    expandindo
    -0.58
     -
    -0.54
    ControllerAdvice
    -0.50
     thats
    -0.50
     —
    -0.49
     thì
    -0.47
    ibi
    -0.47
    以上就是
    -0.47
    ,\
    -0.47
    POSITIVE LOGITS
     something
    0.94
    something
    0.84
     prompting
    0.82
     although
    0.77
     embora
    0.72
    prompt
    0.72
     though
    0.71
    Something
    0.67
     effectively
    0.67
    though
    0.66
    Activations Density 0.377%

    No Known Activations