© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 3897
    Prev
    Next
    INDEX
    Explanations

    conjunctions and conditional phrases that indicate reasoning or relationships in arguments

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

    "and" or "or" followed by a pronoun

    np_acts-logits-general · gemini-2.0-flash

    conjunctions and connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.69
    ulongan
    -0.65
    transQ
    -0.63
     незавершена
    -0.63
    gucig
    -0.62
    testify
    -0.60
     geweſen
    -0.60
     ſeyn
    -0.60
    iſchen
    -0.60
     müſſen
    -0.60
    POSITIVE LOGITS
     hence
    0.32
     doubtless
    0.31
     indeed
    0.30
     cioè
    0.30
     nagu
    0.30
    しかも
    0.29
    наче
    0.29
     daß
    0.27
     perciò
    0.26
    oplayer
    0.26
    Activations Density 0.571%

    No Known Activations