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. 11-GEMMASCOPE-RES-16K
    6. 13388
    Prev
    Next
    INDEX
    Explanations

    days of the week or related temporal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $_['
    -0.68
    rawtypes
    -0.67
     Reef
    -0.66
    4
    -0.66
     Gall
    -0.65
    gb
    -0.65
    halb
    -0.63
     %>
    -0.63
     meta
    -0.63
     pol
    -0.62
    POSITIVE LOGITS
     Thursday
    1.59
     Wednesday
    1.59
    Thursday
    1.56
     Tuesday
    1.54
    Wednesday
    1.53
     Monday
    1.44
    Tuesday
    1.42
     Thursdays
    1.41
     Friday
    1.41
    Friday
    1.39
    Activations Density 0.032%

    No Known Activations