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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1235
    Prev
    Next
    INDEX
    Explanations

    instances of locations and proper nouns in the text

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

    preceding URLs or Twitter handles

    np_acts-logits-general · gemini-2.0-flash

    places and events

    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
    TagMode
    -0.70
     Infórmanos
    -0.67
    뀜
    -0.60
     мәкал
    -0.55
    hoeddwyd
    -0.54
     Administrativna
    -0.54
    StructEnd
    -0.52
    RUnlock
    -0.51
     препратки
    -0.50
    MarshalTo
    -0.50
    POSITIVE LOGITS
     we
    0.50
     they
    0.46
     there
    0.38
     vitesses
    0.35
     geldt
    0.35
     paja
    0.35
     Wikiseite
    0.34
     Hickey
    0.33
     it
    0.33
    Numerade
    0.33
    Activations Density 0.749%

    No Known Activations