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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 20-GEMMASCOPE-RES-16K
    6. 15628
    Prev
    Next
    INDEX
    Explanations

    structured items or entities in a list format

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

    "Fourth" and the number 4

    np_acts-logits-general · gemini-2.0-flash

    fourth / 4

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Secondly
    -0.49
     Second
    -0.49
    Secondly
    -0.45
     FetchType
    -0.45
     Tuesday
    -0.43
     ②
    -0.41
    Second
    -0.41
    ächlich
    -0.40
    abank
    -0.40
     оригіналу
    -0.39
    POSITIVE LOGITS
     fourth
    1.66
    fourth
    1.38
     Fourth
    1.33
    Fourth
    1.31
     FOURTH
    1.27
     vierte
    1.22
     vierten
    1.18
    ④
    1.14
    第四
    1.14
    4
    1.12
    Activations Density 0.446%

    No Known Activations