© 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. 9-GEMMASCOPE-RES-16K
    11. 4595
    Prev
    Next
    INDEX
    Explanations

    affirmative statements related to truth or validity

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

    "True" often followed by mathematical expressions or logical statements

    np_acts-logits-general · gemini-2.0-flash

    true statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    astéroïdes
    -0.49
     سكانية
    -0.47
    vedra
    -0.46
     hornet
    -0.45
     Paket
    -0.45
     ingrat
    -0.45
     Garde
    -0.44
    tshell
    -0.44
    minton
    -0.44
    nadier
    -0.44
    POSITIVE LOGITS
     true
    1.42
     True
    1.40
     truth
    1.38
    True
    1.38
    true
    1.33
     TRUE
    1.27
     Truth
    1.25
    TRUE
    1.23
    truth
    1.19
    Truth
    1.13
    Activations Density 0.238%

    No Known Activations