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. 21-GEMMASCOPE-RES-16K
    6. 8361
    Prev
    Next
    INDEX
    Explanations

    sentences containing affirmative statements about personal feelings or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Incidentally
    -0.82
     erst
    -0.76
    THISDAY
    -0.72
     learnt
    -0.70
     artistes
    -0.69
     IANS
    -0.69
     albeit
    -0.68
    Kaieteur
    -0.66
    🏾
    -0.65
    jooq
    -0.64
    POSITIVE LOGITS
     Concerning
    0.57
    olom
    0.55
     dobbiamo
    0.54
     gouver
    0.53
     visite
    0.52
     jupe
    0.51
     troviamo
    0.50
     possiamo
    0.50
     gắng
    0.49
    einander
    0.49
    Activations Density 0.017%

    No Known Activations