© 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. 20-GEMMASCOPE-RES-16K
    11. 320
    Prev
    Next
    INDEX
    Explanations

    phrases indicating freedom and permissiveness

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

    associated with freedom or being unrestrained

    np_acts-logits-general · gemini-2.0-flash

    unhindered movement and freedom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     CreateTagHelper
    -0.78
     Exacts
    -0.64
    地味
    -0.55
    msgTypes
    -0.53
    makeText
    -0.53
    日閲覧
    -0.52
     <>",
    -0.52
     تكبرها
    -0.52
    agraph
    -0.52
     digno
    -0.51
    POSITIVE LOGITS
     freely
    1.63
     freedom
    1.58
     free
    1.57
     unrestricted
    1.46
     freer
    1.37
     bebas
    1.37
    自由
    1.35
    freedom
    1.34
     loose
    1.33
     libre
    1.32
    Activations Density 0.471%

    No Known Activations