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. 22-GEMMASCOPE-RES-16K
    6. 12802
    Prev
    Next
    INDEX
    Explanations

    correlations between physical symptoms and their severity in relation to various factors

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

    "The more...the [comparative adjective]" construction

    np_acts-logits-general · gemini-2.0-flash

    the more, the more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __(/*!
    -0.56
    LookAnd
    -0.51
    scalatest
    -0.51
     betweenstory
    -0.46
    ConverterFactory
    -0.46
    qtype
    -0.45
     another
    -0.45
    jspx
    -0.45
    zupeł
    -0.45
     GoogleFonts
    -0.44
    POSITIVE LOGITS
     desto
    1.19
     semakin
    1.01
     càng
    0.96
     Чем
    0.84
    越是
    0.84
    ほど
    0.83
     cuanto
    0.82
    เท่า
    0.77
    越
    0.76
    Чем
    0.72
    Activations Density 0.120%

    No Known Activations