© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2617
    Prev
    Next
    INDEX
    Explanations

    specific relationships and roles in various contexts, particularly focusing on associates and categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esternos
    -0.59
    Manbalar
    -0.56
     uLocal
    -0.56
    oredCriteria
    -0.55
    tagHelperRunner
    -0.55
    Personensuche
    -0.54
    Tembelea
    -0.49
    VYMaps
    -0.49
     שוליים
    -0.48
    ValueStyle
    -0.47
    POSITIVE LOGITS
    fromnode
    0.50
     betweenstory
    0.46
     jspb
    0.41
    initComponents
    0.36
    ArgsConstructor
    0.36
     cb
    0.36
     mach
    0.35
     buta
    0.35
     seq
    0.34
     surfer
    0.34
    Activations Density 0.905%

    No Known Activations