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. 20-GEMMASCOPE-RES-16K
    6. 2631
    Prev
    Next
    INDEX
    Explanations

    the name "Frank".

    oai_token-act-pair · gemini-1.5-proTriggered by @rka87338

    references to the name "Frank" and its variations

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

    Tokens starting with "Frank" or containing "furt"

    np_acts-logits-general · gemini-2.0-flash

    frank names and related words

    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
     initComponents
    -0.76
    ThroughAttribute
    -0.74
    StoryboardSegue
    -0.61
    SourceChecksum
    -0.56
     CreateTagHelper
    -0.56
     Generale
    -0.55
     Nunn
    -0.55
    oa̍t
    -0.55
    Erstellt
    -0.54
    NewUrlParser
    -0.54
    POSITIVE LOGITS
    furter
    0.76
     Frankfort
    0.70
     Sinatra
    0.69
    enstein
    0.67
    lyn
    0.63
    lins
    0.63
    Frankie
    0.58
    furt
    0.58
    FRANK
    0.57
     FRANK
    0.56
    Activations Density 0.092%

    No Known Activations