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. 14-GEMMASCOPE-RES-16K
    6. 3919
    Prev
    Next
    INDEX
    Explanations

    repeated references to the term "special" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -1.02
     kaynağından
    -0.98
     Akismet
    -0.92
    SequentialGroup
    -0.91
     CommandType
    -0.85
     Philist
    -0.81
    ResponseWriter
    -0.79
     BufferedImage
    -0.76
    Portale
    -0.76
     Crot
    -0.76
    POSITIVE LOGITS
     special
    1.51
     Special
    1.45
    SPECIAL
    1.41
    Special
    1.35
     SPECIAL
    1.33
    special
    1.30
     speciale
    1.09
     especiales
    1.09
    pecial
    1.07
     specials
    1.04
    Activations Density 0.052%

    No Known Activations