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. 10-GEMMASCOPE-RES-16K
    6. 11650
    Prev
    Next
    INDEX
    Explanations

    geographic locations and associated proper names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     censiti
    -0.56
    gyz
    -0.54
    
    -0.52
    States
    -0.51
    ')))
    -0.50
    ByDefault
    -0.50
    testcase
    -0.49
    \}=
    -0.49
    "]))
    -0.49
     saites
    -0.49
    POSITIVE LOGITS
     village
    0.71
     villagers
    0.68
    帖最后由
    0.68
     villager
    0.63
    InjectAttribute
    0.61
     dekat
    0.57
     paese
    0.57
    sizeCache
    0.57
    tonode
    0.56
    IntOverflow
    0.56
    Activations Density 0.223%

    No Known Activations