© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 11256
    Prev
    Next
    INDEX
    Explanations

    references to bio-related concepts and terminologies

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

    starting with "bio"

    np_acts-logits-general · gemini-2.0-flash

    bioinformatics, bioterrorism, biocompatible

    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
    fjspx
    -0.54
    rzost
    -0.52
    endpush
    -0.49
    sidemargin
    -0.48
     operações
    -0.47
    Personendaten
    -0.46
     handleMessage
    -0.44
     éc
    -0.44
    Apparatus
    -0.42
     Wellen
    -0.42
    POSITIVE LOGITS
     bio
    1.22
     Bio
    1.16
    Bio
    1.09
    bio
    0.98
     BIO
    0.89
    BIO
    0.73
     Bios
    0.71
     био
    0.71
     bios
    0.70
    バイオ
    0.69
    Activations Density 0.131%

    No Known Activations