© 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. 15728
    Prev
    Next
    INDEX
    Explanations

    historical elements and references to origin or dating of events and concepts

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

    dates or dating

    np_acts-logits-general · gemini-2.0-flash

    origins and dates

    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
    AndEndTag
    -0.81
     AssemblyCulture
    -0.67
     الحره
    -0.67
     VIAF
    -0.65
    gameserver
    -0.58
    featureID
    -0.56
     onPostExecute
    -0.56
    yntaxException
    -0.53
    Искәрмәләр
    -0.53
     ब्रेकडाउन
    -0.52
    POSITIVE LOGITS
     dating
    2.06
     dates
    1.69
    dating
    1.67
     Dating
    1.56
     date
    1.49
     dated
    1.47
    Dating
    1.43
     remonte
    1.43
    dates
    1.31
    date
    1.30
    Activations Density 0.395%

    No Known Activations