Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7973
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming and databases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zlich
    -0.42
     podjela
    -0.40
     comparing
    -0.38
     layout
    -0.38
     сен
    -0.38
     dru
    -0.38
    EDEFAULT
    -0.38
    chyma
    -0.37
     transl
    -0.37
    utex
    -0.37
    POSITIVE LOGITS
    WithMany
    0.78
    OneToMany
    0.66
    mappedBy
    0.65
     autorytatywna
    0.64
    BagLayout
    0.61
    EndContext
    0.61
    findpost
    0.59
    ManyToOne
    0.59
     linkovi
    0.57
    OneToOne
    0.54
    Activations Density 0.256%

    No Known Activations