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. 18-GEMMASCOPE-RES-16K
    6. 8778
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts and code structure

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

    Code, URLs, or unusual syntax

    np_acts-logits-general · gemini-2.0-flash

    bracketed lists or sequences

    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
     given
    -0.74
     passed
    -0.69
    paramref
    -0.66
    given
    -0.66
    passed
    -0.60
     param
    -0.60
     parameter
    -0.60
    HasForeignKey
    -0.57
     Passed
    -0.56
     PARAM
    -0.56
    POSITIVE LOGITS
     AssemblyVersion
    0.61
    +:+
    0.56
    HttpPost
    0.56
    ='_
    0.53
    لاه
    0.52
     Corazón
    0.51
     ._
    0.50
    yntaxException
    0.50
    BeginInit
    0.50
     leech
    0.50
    Activations Density 0.453%

    No Known Activations