© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2776
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and specific symbols within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.44
     ciel
    -0.43
    reszcie
    -0.41
    FINALLY
    -0.40
     αντί
    -0.40
     cæ
    -0.40
    gól
    -0.40
    谱
    -0.39
     ſche
    -0.39
    譜
    -0.39
    POSITIVE LOGITS
    Aholisi
    0.72
    Билгалдахарш
    0.65
    Personendaten
    0.64
    ьаж
    0.50
    pexpr
    0.50
     Italijanski
    0.48
     defaultstate
    0.45
    ołnier
    0.44
    __(/*!
    0.44
     تعدى
    0.44
    Activations Density 0.841%

    No Known Activations