© 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. 14219
    Prev
    Next
    INDEX
    Explanations

    common phrases or sayings related to advice or wisdom

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

    Prepositions like "a," "in," or "for"

    np_acts-logits-general · gemini-2.0-flash

    tagline, slogan, motto

    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
     ſind
    -0.71
    SharedDtor
    -0.64
    AndroidJUnit
    -0.61
     μὲν
    -0.61
    ⪜
    -0.60
     Majefty
    -0.60
     doubtnut
    -0.59
    ChildScrollView
    -0.57
     GenerationType
    -0.57
    SBATCH
    -0.57
    POSITIVE LOGITS
     motto
    1.73
     slogan
    1.49
     phrase
    1.32
     proverb
    1.31
     adage
    1.28
     quote
    1.25
     Motto
    1.24
     mantra
    1.23
     tagline
    1.16
     frase
    1.10
    Activations Density 0.368%

    No Known Activations