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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 9653
    Prev
    Next
    INDEX
    Explanations

    symbols or formatting indicators in structured text

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

    Code or configuration file context

    np_acts-logits-general · gemini-2.0-flash

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.64
    at
    -0.48
     let
    -0.46
    con
    -0.46
     Du
    -0.45
     national
    -0.45
    </b>
    -0.45
    <eos>
    -0.44
     National
    -0.44
    and
    -0.43
    POSITIVE LOGITS
     CreateTagHelper
    1.69
    AddTagHelper
    1.31
     AssemblyCulture
    1.19
     Мексичка
    1.15
     للمعارف
    1.15
     MainAxisSize
    1.14
    出版年
    1.11
     FetchType
    1.08
    клопе
    1.07
     Италијани
    1.07
    Activations Density 0.355%

    No Known Activations