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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 901
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ordinal numbers or ranks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RetentionPolicy
    -0.64
    aarrggbb
    -0.64
     initComponents
    -0.58
     resourceCulture
    -0.58
    usahaan
    -0.55
     consciences
    -0.55
    aluz
    -0.54
     تضيفلها
    -0.53
    kmale
    -0.53
     chande
    -0.53
    POSITIVE LOGITS
     graders
    0.86
     anniversary
    0.78
     century
    0.77
     grade
    0.76
     grader
    0.75
     edition
    0.74
     inning
    0.74
    undred
    0.72
    ousand
    0.71
    ousands
    0.69
    Activations Density 0.151%

    No Known Activations