© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14645
    Prev
    Next
    INDEX
    Explanations

    words indicating intent or planning related to business interactions

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

    Followed by a question mark or non-English word

    np_acts-logits-general · gemini-2.0-flash

    doing this, doing it, doing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]")]
    -0.96
    UnusedPrivate
    -0.89
    
    -0.89
    帖最后由
    -0.85
    ंदीखरीदारी
    -0.83
     Drapeau
    -0.81
    principalColumn
    -0.76
    Hauptartikel
    -0.76
    NameInMap
    -0.76
     '\\;'
    -0.75
    POSITIVE LOGITS
     melakukannya
    0.76
     concernés
    0.60
     hacerlo
    0.58
    之意
    0.54
     solchen
    0.53
     createSprite
    0.52
     farlo
    0.52
     doing
    0.51
     procedere
    0.49
    这样做
    0.49
    Activations Density 0.354%

    No Known Activations