© 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. 106
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases related to teaching and learning

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

    Learning how to do something

    np_acts-logits-general · gemini-2.0-flash

    learning or teaching how to do something

    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
    ReusableCell
    -0.93
    enumii
    -0.56
    SignedIn
    -0.53
    chdir
    -0.52
     tartalomajánló
    -0.49
    IVEREF
    -0.47
     terang
    -0.47
    ApiProperty
    -0.46
    而出
    -0.46
    eckel
    -0.46
    POSITIVE LOGITS
     how
    1.16
     basics
    1.05
     basic
    1.00
     techniques
    0.92
    basic
    0.92
     كيفية
    0.85
    how
    0.85
    Basic
    0.84
    basics
    0.81
    Basics
    0.81
    Activations Density 0.187%

    No Known Activations