© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 3907
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal feelings or experiences

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

    unexpectedness or inexplicability

    np_acts-logits-general · gemini-2.0-flash

    for some reason

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.52
    󠁬
    -0.49
    OGND
    -0.47
    IsMutable
    -0.46
     indígen
    -0.45
    GEBURTSDATUM
    -0.45
     Steine
    -0.45
    kkue
    -0.43
    
    -0.42
    
    -0.41
    POSITIVE LOGITS
     somehow
    2.00
     Somehow
    1.84
    Somehow
    1.79
     strangely
    1.43
     irgendwie
    1.26
     weirdly
    1.26
     oddly
    1.24
     mysteriously
    1.17
    なぜか
    1.10
     curiously
    1.05
    Activations Density 0.459%

    No Known Activations