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. 1504
    Prev
    Next
    INDEX
    Explanations

    content related to community unity and collective experience

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

    "blog" or "column" after "last", "this", or "my"

    np_acts-logits-general · gemini-2.0-flash

    previous blog posts

    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
     pungkasnya
    -0.55
    énario
    -0.55
     vettoriale
    -0.53
    ệc
    -0.52
    leih
    -0.50
    gettyimages
    -0.48
    thenReturn
    -0.47
    KeySpec
    -0.47
    Cordialement
    -0.47
    RUnlock
    -0.46
    POSITIVE LOGITS
     blog
    2.31
     Blog
    1.90
    Blog
    1.86
    blog
    1.85
     blogs
    1.82
     blogging
    1.78
     BLOG
    1.72
     posts
    1.54
    BLOG
    1.51
     blogger
    1.45
    Activations Density 0.616%

    No Known Activations