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. 21-GEMMASCOPE-RES-16K
    6. 6546
    Prev
    Next
    INDEX
    Explanations

    terms related to manufacturers and market dynamics

    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
     myſelf
    -0.86
    ſelf
    -0.71
     Majefty
    -0.65
    ſelves
    -0.62
     Jefus
    -0.62
    发表于
    -0.60
     poffible
    -0.58
     ſche
    -0.58
    SPATH
    -0.57
     pleaſure
    -0.57
    POSITIVE LOGITS
     notice
    1.24
     recognizing
    1.20
     noticing
    1.16
     recognize
    1.11
     recognising
    1.08
     recognizes
    1.06
     noticed
    1.03
     Notice
    1.01
     notices
    1.00
     recognise
    1.00
    Activations Density 0.279%

    No Known Activations