© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 3611
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terminology related to processes and conditions in physics and medical contexts

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

    after certain pronouns or nouns

    np_acts-logits-general · gemini-2.0-flash

    no, ceased, not, dropped

    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
     متعلقه
    -0.74
     الحره
    -0.70
     pinulongan
    -0.69
    AndroidJUnit
    -0.59
    īgs
    -0.54
    instancetype
    -0.53
    dersfield
    -0.53
    withstanding
    -0.53
    OnInit
    -0.52
    bulaire
    -0.52
    POSITIVE LOGITS
     no
    2.97
    no
    2.21
    No
    1.53
     NO
    1.51
    不再
    1.46
     now
    1.39
     No
    1.36
    NO
    1.36
     artık
    1.31
     ceased
    1.15
    Activations Density 0.611%

    No Known Activations