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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10078
    Prev
    Next
    INDEX
    Explanations

    sentences with transitions and structured data representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ⓧ
    -0.84
     CURIAM
    -0.59
    -------
    -0.55
     برانيه
    -0.55
    ciple
    -0.54
    блиоте
    -0.54
     compute
    -0.51
     nakalista
    -0.49
     <>",
    -0.49
     esternos
    -0.49
    POSITIVE LOGITS
    UrlResolution
    0.71
    CloseOperation
    0.66
    Chham
    0.66
    FormTagHelper
    0.65
     २०
    0.63
     vuonna
    0.63
    SizeMode
    0.60
     stylo
    0.58
     năm
    0.57
     contemporaneous
    0.56
    Activations Density 0.216%

    No Known Activations