© 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. 7816
    Prev
    Next
    INDEX
    Explanations

    specific details about measurements and adjustments related to products or legal cases

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

    Followed by the word "not"

    np_acts-logits-general · gemini-2.0-flash

    not or NOT

    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
     propOrder
    -0.95
    enumii
    -0.94
    __':
    
    -0.88
    tvguidetime
    -0.82
    rungsseite
    -0.79
    theless
    -0.78
    ")));
    
    -0.77
     disambiguazione
    -0.76
     &___
    -0.76
     INTERESAR
    -0.76
    POSITIVE LOGITS
     not
    2.63
    not
    2.12
     NOT
    1.93
    Not
    1.82
     Not
    1.78
    NOT
    1.76
     bukan
    1.67
     نه
    1.42
     nicht
    1.29
     وليس
    1.24
    Activations Density 0.369%

    No Known Activations