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. 18-GEMMASCOPE-RES-16K
    6. 1557
    Prev
    Next
    INDEX
    Explanations

    financial projections and metrics associated with stock performance

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

    Numerical percentages

    np_acts-logits-general · gemini-2.0-flash

    percentage growth rates

    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
    ########.
    -0.40
     award
    -0.36
     Award
    -0.35
     Walkover
    -0.35
    RTEE
    -0.34
    ]();
    -0.34
     Spot
    -0.34
     ant
    -0.34
    おはようございます
    -0.33
     fal
    -0.33
    POSITIVE LOGITS
     percentage
    1.67
     percentages
    1.67
    percentage
    1.51
     Percentage
    1.46
     (%)
    1.46
     percent
    1.46
    Percentage
    1.38
     PERCENT
    1.36
    percent
    1.35
     yüzde
    1.35
    Activations Density 0.480%

    No Known Activations