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. 19-GEMMASCOPE-RES-16K
    6. 2852
    Prev
    Next
    INDEX
    Explanations

    phrases related to contrast and alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.64
     Mor
    -0.56
    SourceChecksum
    -0.55
    حياته
    -0.50
     “
    -0.50
    :"-"`
    -0.46
     International
    -0.45
    Mor
    -0.42
     Con
    -0.42
    دیگر
    -0.42
    POSITIVE LOGITS
     שוליים
    0.76
    醐
    0.74
     pylint
    0.72
     للمعارف
    0.72
     PrintWriter
    0.70
     Ause
    0.69
    PyExc
    0.69
    databind
    0.68
     GetEnumerator
    0.67
     Repar
    0.67
    Activations Density 0.486%

    No Known Activations