© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 14722
    Prev
    Next
    INDEX
    Explanations

    expressions of concern and positive affirmations in relation to problem-solving

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

    Comes after "Good news", "But", or "luck"

    np_acts-logits-general · gemini-2.0-flash

    good news, luckily, fortunately, thankfully

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]!='
    -0.46
    ViewStyle
    -0.45
    kosi
    -0.44
     watchers
    -0.42
    lippery
    -0.41
     herman
    -0.41
    Gems
    -0.40
    #!/
    -0.40
     SMT
    -0.40
     takers
    -0.39
    POSITIVE LOGITS
    Luckily
    1.17
     Luckily
    1.16
    Fortunately
    1.12
     Fortunately
    1.11
     luckily
    1.11
     fortunately
    1.10
    fortunately
    0.99
    Thankfully
    0.94
     Thankfully
    0.91
     thankfully
    0.81
    Activations Density 0.105%

    No Known Activations