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. 11755
    Prev
    Next
    INDEX
    Explanations

    formal declarations or decisions in legal documents

    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
    selaer
    -0.47
    GoogleApiClient
    -0.45
     './../
    -0.39
    æk
    -0.39
    なりません
    -0.38
    hom
    -0.37
    hap
    -0.37
    FormTagHelper
    -0.37
    ticolo
    -0.37
    chmal
    -0.37
    POSITIVE LOGITS
    Cyfarwyddwr
    0.53
     ExecuteAsync
    0.49
    XmlAccessType
    0.47
     arşivlendi
    0.47
    BASEPATH
    0.47
     aikaa
    0.47
     kaarangay
    0.46
     onward
    0.44
    RTLU
    0.43
     onwards
    0.42
    Activations Density 1.091%

    No Known Activations