© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13743
    Prev
    Next
    INDEX
    Explanations

    contextual expressions of disbelief and surprise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    disbelief or surprise

    np_acts-logits-general · gemini-2.0-flash

    surprise and disbelief

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.58
    ſelves
    -0.57
     tartalomajánló
    -0.55
    Personendaten
    -0.52
    audiovisuel
    -0.50
    IVEREF
    -0.50
     InputDecoration
    -0.50
     autorytatywna
    -0.49
    wiſe
    -0.47
     Photocase
    -0.45
    POSITIVE LOGITS
     disbelief
    0.65
     unbelievable
    0.56
     surprising
    0.55
     astonishing
    0.55
     incred
    0.54
     amazement
    0.54
     sorprend
    0.53
     astonishment
    0.52
     shocking
    0.52
     astonished
    0.51
    Activations Density 0.331%

    No Known Activations