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. 6-GEMMASCOPE-RES-16K
    6. 6754
    Prev
    Next
    INDEX
    Explanations

    elements of critique or analysis regarding social issues and values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.76
    Geplaatst
    -0.70
    __":
    
    -0.69
     للاسماء
    -0.68
     wikihow
    -0.67
    BeginInit
    -0.66
    setVerticalGroup
    -0.66
    ItemBackground
    -0.65
    CppCodeGen
    -0.65
    vespa
    -0.65
    POSITIVE LOGITS
     tough
    0.63
     awfully
    0.58
     alot
    0.56
     very
    0.55
     indeed
    0.54
     nice
    0.53
     brave
    0.51
     quite
    0.51
     heavy
    0.50
     interesting
    0.49
    Activations Density 0.253%

    No Known Activations