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. 25-GEMMASCOPE-RES-16K
    6. 1850
    Prev
    Next
    INDEX
    Explanations

    Japanese phrases that express conditions or uncertainties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeforeEach
    -0.50
    leukin
    -0.45
    
    -0.45
    vierno
    -0.44
    </thead>
    -0.44
     setError
    -0.44
     दू
    -0.42
    тельству
    -0.42
     —
    -0.42
    AfterEach
    -0.41
    POSITIVE LOGITS
    🤣🤣🤣
    0.82
    🤣🤣
    0.82
    😂😂
    0.81
     😂😂😂
    0.80
    wwwwwwww
    0.80
    😂😂😂
    0.76
     😂😂
    0.76
    😂
    0.76
    なんですが
    0.75
     Efq
    0.74
    Activations Density 0.256%

    No Known Activations