© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 3320
    Prev
    Next
    INDEX
    Explanations

    specific molecular structures related to cardiac interventions and devices

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

    Tokens before "ben", "rip", or inside parentheses after "quad" or "tetra"

    np_acts-logits-general · gemini-2.0-flash

    prefixes for numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     menetap
    -0.41
     gelungen
    -0.40
    ínű
    -0.40
     Rechten
    -0.40
     Wiese
    -0.40
    MathML
    -0.38
     tartalomajánló
    -0.38
     aprecia
    -0.35
     Entsche
    -0.35
     θέ
    -0.35
    POSITIVE LOGITS
     tri
    0.67
     Quad
    0.66
     Tri
    0.63
    parsedMessage
    0.61
     Tetra
    0.60
     quad
    0.59
     tetra
    0.58
     quadri
    0.57
     propOrder
    0.56
     Tet
    0.54
    Activations Density 0.320%

    No Known Activations