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. 2866
    Prev
    Next
    INDEX
    Explanations

    sound-related terms and descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Normdatei
    -0.86
     beginnetje
    -0.84
    ſelf
    -0.81
     Majefty
    -0.78
     raiſ
    -0.78
     myſelf
    -0.76
    ſelves
    -0.72
    WebVitals
    -0.71
     Efq
    -0.71
     fevere
    -0.71
    POSITIVE LOGITS
     bang
    1.54
     boom
    1.18
     thud
    1.17
     BANG
    1.15
    bang
    1.15
     Bang
    1.09
    Bang
    1.09
    boom
    1.01
    BANG
    1.00
     thump
    0.98
    Activations Density 0.110%

    No Known Activations