© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 3866
    Prev
    Next
    INDEX
    Explanations

    instances of phrases indicating permission or allowance

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

    Followed by verbs

    np_acts-logits-general · gemini-2.0-flash

    token followed by specific token

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vece
    -0.48
    TestFixture
    -0.46
    etak
    -0.45
     giuri
    -0.43
    nonatomic
    -0.43
    must
    -0.43
     Aseg
    -0.42
     deber
    -0.42
     weshalb
    -0.42
    Clk
    -0.41
    POSITIVE LOGITS
     loose
    0.87
     slide
    0.80
     slip
    0.80
     know
    0.79
    bootstrapcdn
    0.74
     alone
    0.72
     BorderRadius
    0.70
     breathe
    0.70
     be
    0.69
     ProtoMessage
    0.69
    Activations Density 0.205%

    No Known Activations