© 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. 592
    Prev
    Next
    INDEX
    Explanations

    phrases related to avoidance or evasion of certain actions or behaviors

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

    "avoid" or its variations

    np_acts-logits-general · gemini-2.0-flash

    avoiding things

    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
    ReusableCell
    -0.51
     argint
    -0.49
     $("<
    -0.46
     _("
    -0.46
     QtCore
    -0.45
     inoxydable
    -0.45
     belangrij
    -0.45
     métallique
    -0.44
    Germain
    -0.44
     membri
    -0.44
    POSITIVE LOGITS
    avoid
    1.16
     AVOID
    1.13
    Avoid
    1.12
     avoid
    1.10
     Avoid
    1.06
     avoidance
    1.04
     avoids
    1.02
     avoiding
    1.01
    Avoiding
    1.01
     avoided
    1.00
    Activations Density 0.143%

    No Known Activations