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. 5-GEMMASCOPE-RES-16K
    6. 4792
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to terms of agreements and regulatory compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIOException
    -0.48
    Ditto
    -0.44
    penup
    -0.43
    AddRange
    -0.43
     Bar
    -0.41
     Jost
    -0.41
     pon
    -0.41
    つぶ
    -0.40
     pop
    -0.40
     jog
    -0.40
    POSITIVE LOGITS
     jadx
    0.74
     Houſe
    0.74
     houſe
    0.71
     greateſt
    0.71
    LookAnd
    0.69
     Eſ
    0.69
    Portale
    0.68
    LEncoder
    0.67
     requirements
    0.67
    SBATCH
    0.67
    Activations Density 0.605%

    No Known Activations