Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 1579
    Prev
    Next
    INDEX
    Explanations

    colons and their surrounding punctuation or spacing in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     PWN
    -0.97
     myſelf
    -0.85
     laun
    -0.85
     Brenn
    -0.83
     كومونز
    -0.83
    )+"
    -0.82
     fevere
    -0.80
    `}
    -0.79
     ſame
    -0.77
    RouterModule
    -0.75
    POSITIVE LOGITS
    いる
    0.98
     Humphries
    0.98
     :
    0.93
     Rosenthal
    0.91
    ::::::::
    0.86
    iwa
    0.86
    sertation
    0.84
    出版年
    0.84
     Ayres
    0.84
     ;
    0.79
    Activations Density 0.108%

    No Known Activations