Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 1578
    Prev
    Next
    INDEX
    Explanations

    variations of the name "Phil" or "Philip."

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

    Tokens before middle or last names starting with certain letters

    np_acts-logits-general · gemini-2.0-flash

    philip, felipe, and related names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -1.06
    +#+#
    -1.06
     CreateTagHelper
    -1.00
     للمعارف
    -0.84
     doInBackground
    -0.83
    Datuak
    -0.83
     الرياضيه
    -0.78
     invokingState
    -0.78
    сылкі
    -0.78
     تضيفلها
    -0.78
    POSITIVE LOGITS
     Fil
    0.60
     pil
    0.54
    IPP
    0.53
     fil
    0.53
     Phil
    0.49
     ки
    0.47
    Fil
    0.46
    opher
    0.45
    omen
    0.43
     keh
    0.43
    Activations Density 0.123%

    No Known Activations