© 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. 20-GEMMASCOPE-RES-16K
    6. 248
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics

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

    the number two

    np_acts-logits-general · gemini-2.0-flash

    numeric sequences

    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
     inherit
    -0.52
     inherited
    -0.47
    inher
    -0.46
    Implicit
    -0.44
    Hindu
    -0.43
     Hindu
    -0.42
    herit
    -0.41
     inher
    -0.41
     Hirst
    -0.40
    inherit
    -0.40
    POSITIVE LOGITS
    .*")]
    1.01
    principalTable
    0.88
    DockStyle
    0.85
    ReusableCell
    0.85
     Waray
    0.81
    AutoScaleMode
    0.76
    RTEE
    0.75
    setVerticalGroup
    0.74
     téléphonique
    0.73
     OFDb
    0.73
    Activations Density 0.236%

    No Known Activations