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. 11-GEMMASCOPE-RES-16K
    6. 5506
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports achievements and records

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reſ
    -0.70
     Inſ
    -0.59
     Houſe
    -0.59
     pleaſure
    -0.56
     Beſ
    -0.52
     greateſt
    -0.52
     Theſe
    -0.52
     Perſ
    -0.50
     Majefty
    -0.50
     ―――――
    -0.49
    POSITIVE LOGITS
    SequentialGroup
    0.81
    Бахар
    0.75
    twimg
    0.66
    enterOuterAlt
    0.64
    DIPSETTING
    0.58
     Dodson
    0.54
    abestanden
    0.54
     co
    0.54
     dis
    0.54
    igshid
    0.53
    Activations Density 0.519%

    No Known Activations