© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 13765
    Prev
    Next
    INDEX
    Explanations

    phrases and words associated with academic or scholarly articles

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

    Sentences about articles/papers

    np_acts-logits-general · gemini-2.0-flash

    describing content origin or availability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    complexType
    -0.73
    OGND
    -0.65
    NOPQRST
    -0.63
     propOrder
    -0.63
     handleMessage
    -0.62
     eventdata
    -0.62
    celotti
    -0.61
    andExpect
    -0.60
    RUnlock
    -0.60
    Obrázky
    -0.60
    POSITIVE LOGITS
     courtesy
    1.00
     originally
    0.99
     sponsored
    0.81
    originally
    0.76
     adapted
    0.76
     Originally
    0.73
     cortesía
    0.72
     excer
    0.72
    Originally
    0.71
     contributed
    0.70
    Activations Density 0.335%

    No Known Activations