© 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-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 6501
    Prev
    Next
    INDEX
    Explanations

    the frequency of the substring "ch" in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.78
     GenerationType
    -0.63
    KEA
    -0.61
     تضيفلها
    -0.61
     Económica
    -0.60
    ]();
    -0.60
     Wiktionnaire
    -0.59
    허
    -0.59
    vernment
    -0.58
    '''
    -0.58
    POSITIVE LOGITS
    ch
    3.32
    CH
    1.64
    chs
    1.11
    chman
    1.11
    chn
    1.03
    chl
    1.00
    chm
    0.98
    х
    0.97
     ch
    0.92
    chy
    0.90
    Activations Density 0.095%

    No Known Activations