© 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. 20-GEMMASCOPE-RES-16K
    11. 7870
    Prev
    Next
    INDEX
    Explanations

    personal opinions and sentiments expressed in the text

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

    First-person opinion/belief

    np_acts-logits-general · gemini-2.0-flash

    personal beliefs and opinions

    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
    ########.
    -0.98
     فريبيس
    -0.74
     AssemblyProduct
    -0.72
    ChildIndex
    -0.55
    AutoScaleMode
    -0.53
     оригіналу
    -0.52
     wireType
    -0.51
    calaure
    -0.51
    expandindo
    -0.51
    matchCondition
    -0.50
    POSITIVE LOGITS
     believe
    2.15
     believes
    1.99
    believe
    1.82
     belief
    1.81
     believed
    1.66
    belie
    1.59
     think
    1.58
     believing
    1.55
     Believe
    1.53
     opinion
    1.53
    Activations Density 0.598%

    No Known Activations