© 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. 505
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the frequency or commonality of certain events or data

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

    "recent" or "recently"

    np_acts-logits-general · gemini-2.0-flash

    recent or recently

    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
     domani
    -0.50
    CGRectMake
    -0.50
     semula
    -0.47
    getOriginal
    -0.46
     bestehenden
    -0.46
    mybatisplus
    -0.44
     demain
    -0.44
    moveToFirst
    -0.44
    PRWEB
    -0.44
     CGRectMake
    -0.44
    POSITIVE LOGITS
     recent
    3.28
    recent
    2.77
     recently
    2.72
    Recent
    2.54
     Recent
    2.50
     recente
    2.43
    recently
    2.41
     RECENT
    2.39
     Recently
    2.36
    Recently
    2.32
    Activations Density 0.448%

    No Known Activations