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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 13173
    Prev
    Next
    INDEX
    Explanations

    assertions and perspectives regarding expectations and opinions

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

    "I'm sure" or a similar expression

    np_acts-logits-general · gemini-2.0-flash

    I'm sure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     apparently
    -1.08
     Apparently
    -1.00
    apparently
    -0.97
    Apparently
    -0.88
    居然
    -0.82
     aparentemente
    -0.82
     actually
    -0.82
     reportedly
    -0.81
    似乎
    -0.80
    竟然
    -0.80
    POSITIVE LOGITS
     algún
    0.73
     alguno
    0.70
    plenty
    0.70
     plenty
    0.69
     algum
    0.68
    cektir
    0.65
     irgendwo
    0.65
     somewhere
    0.65
    bootstrapcdn
    0.63
     alguna
    0.62
    Activations Density 0.442%

    No Known Activations