© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 3934
    Prev
    Next
    INDEX
    Explanations

    negative affirmations

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

    Followed by negative verb

    np_acts-logits-general · gemini-2.0-flash

    never followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    AISSEE
    -0.66
    NameInMap
    -0.65
    GOTREF
    -0.62
    complexType
    -0.61
    IBOutlet
    -0.61
    setupUi
    -0.60
     متحده
    -0.58
    ukone
    -0.57
     Enix
    -0.57
     Winaray
    -0.56
    POSITIVE LOGITS
     never
    1.04
     Never
    1.02
    Never
    1.01
     NEVER
    1.00
    never
    1.00
    NEVER
    0.96
     ever
    0.96
     EVER
    0.84
    ever
    0.80
     jamás
    0.73
    Activations Density 0.066%

    No Known Activations