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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 4021
    Prev
    Next
    INDEX
    Explanations

    the presence of specific proper nouns and intent-related keywords in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    limite
    -0.56
    localPosition
    -0.54
     campo
    -0.52
    LookAnd
    -0.52
     campos
    -0.51
    expandindo
    -0.51
    atoria
    -0.50
     Duckworth
    -0.50
     otim
    -0.50
    AlterField
    -0.50
    POSITIVE LOGITS
    Intent
    1.03
    awtextra
    0.75
     kasarigan
    0.70
     CreateTagHelper
    0.70
     محفوظة
    0.67
    isset
    0.65
     linkovi
    0.63
    ValueStyle
    0.62
     ब्रेकडाउन
    0.62
    TestTools
    0.62
    Activations Density 0.277%

    No Known Activations