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. 22-GEMMASCOPE-RES-16K
    6. 10511
    Prev
    Next
    INDEX
    Explanations

    references to worship and belief in God

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

    Islamic terms or concepts

    np_acts-logits-general · gemini-2.0-flash

    daily prayers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.91
     متعلقه
    -0.81
    migrationBuilder
    -0.78
    aarrggbb
    -0.78
     оригіналу
    -0.70
    ISupport
    -0.69
    ModelSerializer
    -0.69
    LabelTagHelper
    -0.67
     BoxFit
    -0.65
     Diakses
    -0.64
    POSITIVE LOGITS
     Ins
    1.21
    Ins
    1.09
     ins
    0.97
     Al
    0.86
    ins
    0.84
     Allah
    0.82
     praise
    0.80
     Praise
    0.79
    Al
    0.77
    Allah
    0.72
    Activations Density 0.165%

    No Known Activations