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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 1992
    Prev
    Next
    INDEX
    Explanations

    references to legal obligations or directives related to intellectual property

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    存于互联网档案馆
    -0.77
    لينكات
    -0.68
     AssemblyTitle
    -0.66
     فريبيس
    -0.64
    StoreMessageInfo
    -0.63
     <<<<<<<<<<<<<<
    -0.61
     intptr
    -0.61
    FilterChain
    -0.60
     SQLITE
    -0.58
    mtrl
    -0.57
    POSITIVE LOGITS
     hereby
    0.91
     implore
    0.83
     invite
    0.77
     salute
    0.76
     urge
    0.76
     request
    0.75
     thank
    0.69
     respectfully
    0.68
     pledge
    0.67
     suggest
    0.67
    Activations Density 0.362%

    No Known Activations