© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 8719
    Prev
    Next
    INDEX
    Explanations

    words that indicate existence or state of being

    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
     seseorang
    -0.65
     lèvres
    -0.61
     someone
    -0.58
     démocr
    -0.58
     gouvernements
    -0.58
    someone
    -0.57
     iemand
    -0.57
     pouvoirs
    -0.56
     énergé
    -0.53
     côtés
    -0.53
    POSITIVE LOGITS
     themselves
    1.10
     those
    1.07
     ones
    1.06
    themselves
    1.03
     originals
    0.94
    principalTable
    0.93
     examples
    0.93
     replacements
    0.92
    those
    0.91
     những
    0.91
    Activations Density 0.699%

    No Known Activations