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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 17-GEMMASCOPE-RES-16K
    6. 10989
    Prev
    Next
    INDEX
    Explanations

    references to historical developments and social structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fraî
    -0.51
     volonté
    -0.49
     couverts
    -0.49
    nende
    -0.47
    SPECIFIED
    -0.47
     maggiori
    -0.45
     immediately
    -0.45
    甫
    -0.45
    thane
    -0.43
     immediatamente
    -0.43
    POSITIVE LOGITS
     become
    1.16
    become
    1.05
     became
    1.02
     becoming
    1.01
     becomes
    0.96
    became
    0.95
     Become
    0.93
    becomes
    0.91
    Become
    0.89
     devenu
    0.89
    Activations Density 0.298%

    No Known Activations