© 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. 21-GEMMASCOPE-RES-16K
    6. 15350
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and expressions of opinion or experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VolleyError
    -0.52
    akum
    -0.51
    ThemeOverlay
    -0.48
     bej
    -0.47
    ParallelGroup
    -0.47
    ActivityResult
    -0.46
    respond
    -0.46
     Dernière
    -0.44
     desempe
    -0.44
    PropertyGroup
    -0.44
    POSITIVE LOGITS
     wished
    0.85
     wish
    0.75
     wishes
    0.69
     recommend
    0.68
     normally
    0.67
    Normally
    0.67
     advis
    0.66
     expected
    0.65
     Recommend
    0.65
     Рекоменду
    0.65
    Activations Density 0.153%

    No Known Activations