Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-GEMMASCOPE-RES-16K
    6. 11974
    Prev
    Next
    INDEX
    Explanations

    the word "only" in various contexts to emphasize exclusivity or uniqueness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vectorielle
    -0.68
     vectorielles
    -0.65
     abstrait
    -0.62
     meurt
    -0.57
    erçe
    -0.56
     magari
    -0.56
     externi
    -0.55
     fuoco
    -0.54
     oppure
    -0.53
     barbati
    -0.52
    POSITIVE LOGITS
    satunya
    1.29
    parsedMessage
    0.99
    ")){
    
    0.96
    ]")]
    0.89
     jedin
    0.89
    "]]
    0.84
    findpost
    0.83
    DockStyle
    0.83
    )‏
    0.83
     '{@
    0.82
    Activations Density 0.036%

    No Known Activations