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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 5038
    Prev
    Next
    INDEX
    Explanations

    references to technology and its applications in communication and health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.53
     elettrico
    -0.52
     menahan
    -0.51
     défend
    -0.50
     marrone
    -0.50
     exemplaires
    -0.49
     differenza
    -0.48
    allos
    -0.48
     plainte
    -0.48
     détach
    -0.47
    POSITIVE LOGITS
    Personendaten
    0.78
     متعلقه
    0.76
    csolódó
    0.74
     Roskov
    0.72
     personalized
    0.71
    aarrggbb
    0.71
     personalised
    0.69
     actionable
    0.69
     offline
    0.68
    맞
    0.67
    Activations Density 0.595%

    No Known Activations