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. 5240
    Prev
    Next
    INDEX
    Explanations

    words related to matters of identity and self

    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
     itſelf
    -1.79
     themſelves
    -1.59
    AsUp
    -1.56
     iſt
    -1.50
     myſelf
    -1.50
     ſever
    -1.44
     ſind
    -1.42
     himſelf
    -1.41
     Efq
    -1.41
     faſt
    -1.40
    POSITIVE LOGITS
     the
    1.09
     an
    0.97
     a
    0.97
     
    0.94
     p
    0.79
     "
    0.78
     e
    0.78
     n
    0.76
     this
    0.72
     f
    0.72
    Activations Density 0.145%

    No Known Activations