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

    Neuronpedia

    Jacobian LensNEW
    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. 14792
    Prev
    Next
    INDEX
    Explanations

    phrases related to the need for representation and support in various contexts

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

    following "be," "are," or "is"

    np_acts-logits-general · gemini-2.0-flash

    provided for

    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
    Diz
    -0.52
     designed
    -0.50
    designed
    -0.50
     mar
    -0.47
    stal
    -0.46
     Mack
    -0.45
     Mar
    -0.43
     u
    -0.41
     Must
    -0.41
     dibutuhkan
    -0.40
    POSITIVE LOGITS
     represented
    1.31
     covered
    1.21
     catered
    1.16
     serviced
    1.12
     accommodated
    1.12
     handled
    1.08
     served
    1.04
     Covered
    1.02
    represented
    1.01
     Served
    1.01
    Activations Density 0.584%

    No Known Activations