© 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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1920
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to biological analysis and research methodologies

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

    scientific or research methods

    np_acts-logits-general · gemini-2.0-flash

    biological and scientific terms followed by experimental details

    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
     Fiscalía
    -0.42
     Lázaro
    -0.40
     Meksi
    -0.40
    Accademia
    -0.40
     Samaria
    -0.40
     Avrupa
    -0.39
     Castelo
    -0.39
     Francia
    -0.39
     Navidad
    -0.39
     Pacífico
    -0.39
    POSITIVE LOGITS
     Result
    0.82
     Means
    0.82
     Needed
    0.81
     Needs
    0.80
     Coverage
    0.77
     Work
    0.76
     Away
    0.75
     Enough
    0.75
     Possible
    0.75
     Potential
    0.75
    Activations Density 2.742%

    No Known Activations