© 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. 20-GEMMASCOPE-RES-16K
    11. 3629
    Prev
    Next
    INDEX
    Explanations

    timestamps and references to specific periods or events

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

    Follows "from [time/place] on" or directional words

    np_acts-logits-general · gemini-2.0-flash

    point on or now on

    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
    |}{}
    -0.56
    جوايز
    -0.53
    baomidou
    -0.52
    tées
    -0.49
    acular
    -0.48
    idhi
    -0.48
    نج
    -0.47
    achable
    -0.46
     regener
    -0.46
    vaient
    -0.45
    POSITIVE LOGITS
     onwards
    2.23
     onward
    1.99
     forward
    1.39
     upwards
    1.31
    forward
    1.20
     upward
    1.15
     downwards
    1.14
     forwards
    1.13
     adelante
    1.10
    Forward
    1.03
    Activations Density 0.181%

    No Known Activations