Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5446
    Prev
    Next
    INDEX
    Explanations

    themes related to emotional connections and experiences

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

    preceding "us", "me", "him"

    np_acts-logits-general · gemini-2.0-flash

    verbs of action and causation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fromnode
    -0.59
    windowFixed
    -0.58
    endpush
    -0.57
    retudo
    -0.56
    issory
    -0.55
     للمعارف
    -0.54
    Yourself
    -0.54
    esgue
    -0.52
     Lingkungan
    -0.51
    
    -0.50
    POSITIVE LOGITS
     us
    0.55
     me
    0.37
    httphttps
    0.35
     allow
    0.35
     allows
    0.34
     further
    0.33
     our
    0.32
    unte
    0.31
     you
    0.31
     kom
    0.31
    Activations Density 0.702%

    No Known Activations