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. 10396
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "one" in various contexts

    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
    IntoConstraints
    -0.73
    Бахар
    -0.63
     Shaksp
    -0.62
     Majefty
    -0.61
    dega
    -0.58
     kasarigan
    -0.58
    Scénario
    -0.57
    енча
    -0.56
     arcs
    -0.56
     bores
    -0.56
    POSITIVE LOGITS
    ResumeLayout
    0.64
     Normdatei
    0.60
    onViewCreated
    0.60
     مشين
    0.58
    ngOnInit
    0.57
    '),
    
    0.56
    Šaltiniai
    0.54
    )),
    
    0.54
    \{\\
    0.53
    WithIOException
    0.53
    Activations Density 0.109%

    No Known Activations