© 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. 23-GEMMASCOPE-RES-16K
    6. 9595
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of people and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rayas
    -0.46
     skrift
    -0.45
     ferons
    -0.44
     religieuses
    -0.42
     estric
    -0.41
     mijne
    -0.41
     estrictamente
    -0.41
     zanahoria
    -0.41
     múltiple
    -0.41
     nothwendig
    -0.40
    POSITIVE LOGITS
     Administrativna
    0.67
    adaptiveStyles
    0.61
     Italijani
    0.54
     uVar
    0.52
    Rhestr
    0.52
    fromnode
    0.50
     AttributeSet
    0.50
     setError
    0.50
     BaseActivity
    0.50
     nahilalakip
    0.49
    Activations Density 0.344%

    No Known Activations