© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 13213
    Prev
    Next
    INDEX
    Explanations

    infinitive verbs and prepositions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ainfi
    -0.64
     zelve
    -0.62
     étoient
    -0.61
    VYMaps
    -0.60
    __*/
    -0.60
     resourceCulture
    -0.59
    ftagPool
    -0.58
    berdayakan
    -0.56
    fjspx
    -0.56
    majánló
    -0.56
    POSITIVE LOGITS
     към
    1.28
     zum
    1.25
     إلى
    1.23
     zu
    1.23
     unto
    1.19
     zur
    1.18
     to
    1.16
    到
    1.16
     To
    1.16
     đến
    1.15
    Activations Density 0.117%

    No Known Activations