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

    Neuronpedia

    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. 12-GEMMASCOPE-RES-16K
    11. 15189
    Prev
    Next
    INDEX
    Explanations

    phrases related to licensing agreements and permissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uot
    -0.42
     Walkover
    -0.38
    uteria
    -0.37
    杓
    -0.36
     actually
    -0.36
    不定
    -0.35
    Manipulation
    -0.34
     вз
    -0.34
    Gesamt
    -0.33
    奉
    -0.32
    POSITIVE LOGITS
     nahilalakip
    0.77
    RegistryLite
    0.69
    تقاوى
    0.67
    ngdoc
    0.65
     TestBed
    0.65
     protoimpl
    0.64
    تفصیلات
    0.63
     '\\;'
    0.61
     lenker
    0.59
    EDEFAULT
    0.59
    Activations Density 0.872%

    No Known Activations