© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 36282
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the substring "ab" in various contexts

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

    sequence 'ab'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.59
    unggulan
    -0.55
    তথ্যসূত্র
    -0.52
    peri
    -0.51
    perry
    -0.47
     disambiguazione
    -0.46
     industrias
    -0.45
    myr
    -0.45
     acompaña
    -0.45
    environnement
    -0.44
    POSITIVE LOGITS
    ab
    2.59
    AB
    1.78
     ab
    1.78
    Ab
    1.63
     Ab
    1.56
     AB
    1.39
    اب
    1.07
    аб
    0.98
    aab
    0.98
    abb
    0.96
    Activations Density 0.019%

    No Known Activations