© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 14280
    Prev
    Next
    INDEX
    Explanations

    financial disparities and comparisons between genders

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

    Indicates relative size or amount

    np_acts-logits-general · gemini-2.0-flash

    magnitude or comparison

    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
     оригіналу
    -0.47
    MENAFN
    -0.47
    mybatisplus
    -0.46
    ══
    -0.46
    MigrationBuilder
    -0.43
    ]:
    -0.43
    igens
    -0.42
    vey
    -0.41
    الإنجليزية
    -0.41
    _));
    -0.41
    POSITIVE LOGITS
     twice
    1.18
     doppelt
    1.14
     considerably
    1.14
     significantly
    1.09
    significantly
    1.03
    比
    1.02
     substantially
    1.01
     вд
    1.01
    twice
    0.98
     Twice
    0.95
    Activations Density 0.498%

    No Known Activations