© 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. 16029
    Prev
    Next
    INDEX
    Explanations

    technical terms related to networking and internet protocols

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

    Preceding words before personal pronouns

    np_acts-logits-general · gemini-2.0-flash

    cours et jeux sur ubuntu

    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
    mographie
    -0.56
    anskje
    -0.53
    onent
    -0.50
    roskop
    -0.50
    ichthys
    -0.49
     culturelle
    -0.49
     FORMATION
    -0.49
    aterdag
    -0.49
    PRESENT
    -0.49
     LUNCH
    -0.49
    POSITIVE LOGITS
     based
    0.63
     tailored
    0.56
    ReusableCell
    0.53
     multic
    0.53
     multil
    0.52
    low
    0.51
    typeid
    0.51
     multi
    0.50
     online
    0.50
     typu
    0.50
    Activations Density 0.088%

    No Known Activations