© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13231
    Prev
    Next
    INDEX
    Explanations

    phrases indicating necessity or lack thereof

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

    after "need" (followed by "to")

    np_acts-logits-general · gemini-2.0-flash

    need to perform action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     suaminya
    -0.40
     montée
    -0.37
    alyptus
    -0.34
    warted
    -0.33
     résine
    -0.33
    ,$_
    -0.32
     posibilidades
    -0.32
     jouet
    -0.31
     Comprometido
    -0.31
     setempat
    -0.31
    POSITIVE LOGITS
    不必
    0.69
    只需
    0.68
    只需要
    0.66
     hoeft
    0.64
    无需
    0.63
     unnecessary
    0.62
    不需要
    0.59
    也不用
    0.59
    不用
    0.59
    굳
    0.58
    Activations Density 0.337%

    No Known Activations