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. 3029
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or sequential events

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

    Text preceding time-related conjunctions

    np_acts-logits-general · gemini-2.0-flash

    sudden events when

    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
    tagHelperRunner
    -0.60
     VizieR
    -0.59
    éndolo
    -0.59
     Вікіпе
    -0.58
    Demografie
    -0.51
    innis
    -0.50
    ͝
    -0.48
    κολου
    -0.47
     volledige
    -0.47
     campaigned
    -0.46
    POSITIVE LOGITS
     suddenly
    1.97
     Suddenly
    1.81
    Suddenly
    1.73
    suddenly
    1.71
     soudain
    1.34
     sudden
    1.33
    突然
    1.31
    忽然
    1.29
     plötzlich
    1.27
     вдруг
    1.24
    Activations Density 0.316%

    No Known Activations