© 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. 14-GEMMASCOPE-RES-16K
    11. 9871
    Prev
    Next
    INDEX
    Explanations

    concepts related to existence, presence, and validity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kä
    -0.40
    centerTitle
    -0.40
     ideal
    -0.38
     voudrais
    -0.38
    Exclusive
    -0.37
    ähr
    -0.37
     invitamos
    -0.36
     IDEAL
    -0.35
     Ideal
    -0.35
    SHARED
    -0.35
    POSITIVE LOGITS
     contextLoads
    0.63
    existence
    0.59
     existence
    0.56
    Existence
    0.54
     protoimpl
    0.54
     hasNext
    0.54
     Existence
    0.53
    Bibliograf
    0.53
    SPATH
    0.52
     EXISTS
    0.50
    Activations Density 0.834%

    No Known Activations