© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2403
    Prev
    Next
    INDEX
    Explanations

    negative words and phrases related to rejection or disapproval

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

    numerical sequences or strings with numerical characters.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     Heiligen
    -0.40
    ✭✭
    -0.38
     Spez
    -0.38
     Erben
    -0.34
    ucoup
    -0.34
     enfans
    -0.33
     APPLY
    -0.33
     高等
    -0.33
    enquête
    -0.32
     scolaires
    -0.32
    POSITIVE LOGITS
    ValueStyle
    0.91
     autorytatywna
    0.86
    AddTagHelper
    0.78
     CreateTagHelper
    0.77
    تقاوى
    0.73
     незавершена
    0.71
     OMITBAD
    0.68
    rungsseite
    0.66
     '\\;'
    0.66
    httphttps
    0.66
    Activations Density 0.010%

    No Known Activations