© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 4942
    Prev
    Next
    INDEX
    Explanations

    technical terminologies and concepts related to biology, particularly concerning proteins, liquids, and microorganisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     heapq
    -0.56
    ocarditis
    -0.55
    tagHelperRunner
    -0.53
    
    -0.53
     wikipagina
    -0.52
    odymium
    -0.52
    ussis
    -0.52
     myſelf
    -0.52
     AVL
    -0.50
     queſta
    -0.49
    POSITIVE LOGITS
    Tembelea
    0.39
     pride
    0.36
     invitamos
    0.36
     Arbeit
    0.35
     Mul
    0.35
    Mock
    0.35
    UnknownFieldSet
    0.35
     Breite
    0.34
     Brücke
    0.34
     SAFETY
    0.33
    Activations Density 2.716%

    No Known Activations