© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5482
    Prev
    Next
    INDEX
    Explanations

    references to various entities, conditions, or aspects that categorize or differentiate elements in a context

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

    Followed by certain nouns

    np_acts-logits-general · gemini-2.0-flash

    other followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
     either
    -0.33
    InstrumentedTest
    -0.31
    either
    -0.30
     fær
    -0.29
    roughts
    -0.29
     both
    -0.28
    TableModel
    -0.28
    TestTools
    -0.28
     Especially
    -0.27
    sekten
    -0.26
    POSITIVE LOGITS
     jspb
    0.64
     Chwiliwch
    0.64
    aarrggbb
    0.63
     beginnetje
    0.63
     '\\;'
    0.60
    +#+#
    0.59
    Tikang
    0.56
     iprot
    0.56
     ſind
    0.55
    enderror
    0.55
    Activations Density 0.196%

    No Known Activations