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. 22-GEMMASCOPE-RES-16K
    6. 13767
    Prev
    Next
    INDEX
    Explanations

    repeated references to "the" and specific historical events or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The end of a period of time

    np_acts-logits-general · gemini-2.0-flash

    the end of time periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     futuras
    -0.42
    right
    -0.41
    as
    -0.40
    no
    -0.39
    了一眼
    -0.38
    marginLeft
    -0.37
    we
    -0.36
    ges
    -0.35
    Right
    -0.34
     espor
    -0.34
    POSITIVE LOGITS
     onset
    1.12
     start
    1.07
     conclusion
    1.07
     beginning
    0.99
     end
    0.97
     height
    0.96
    conclusion
    0.95
    beginning
    0.90
     midpoint
    0.89
     outbreak
    0.89
    Activations Density 0.342%

    No Known Activations