© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 879
    Prev
    Next
    INDEX
    Explanations

    words that convey emotional quality or evaluative judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ა
    -0.52
    <eos>
    -0.48
    wer
    -0.45
     or
    -0.44
    lah
    -0.44
     generally
    -0.44
     
    -0.43
    inc
    -0.43
    ime
    -0.42
    ்க
    -0.42
    POSITIVE LOGITS
     pleaſure
    1.34
     purpoſe
    1.34
     myſelf
    1.34
     raiſ
    1.31
     themſelves
    1.29
     houſe
    1.28
     itſelf
    1.27
     Efq
    1.27
     Monfieur
    1.25
     ſeveral
    1.25
    Activations Density 0.973%

    No Known Activations