© 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. 15276
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to user-friendliness and accessibility in products or services

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

    preceding "friendly" or describing resistance

    np_acts-logits-general · gemini-2.0-flash

    -friendly and -resistant suffixes

    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
    InitVars
    -0.53
     ļ
    -0.52
    ValueGenerated
    -0.49
     résult
    -0.48
    Begriffsklä
    -0.48
     Theſe
    -0.48
    ագրություններ
    -0.48
    ViewFeatures
    -0.47
     poffe
    -0.47
     vermittelt
    -0.47
    POSITIVE LOGITS
     friendly
    1.78
    friendly
    1.48
     Friendly
    1.42
    Friendly
    1.38
     proof
    1.33
    proof
    1.22
     FRIEND
    1.22
    Proof
    1.18
     compatible
    1.16
     Proof
    1.13
    Activations Density 0.257%

    No Known Activations