© 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. 24-GEMMASCOPE-RES-16K
    6. 16224
    Prev
    Next
    INDEX
    Explanations

    references to specific researchers or authors

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

    Tokens starting with "Tak" or "Nak"

    np_acts-logits-general · gemini-2.0-flash

    Tak, Sak, Nak, Bak names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     viewDidLoad
    -0.67
    ه
    -0.65
    __(/*!
    -0.62
    es
    -0.55
    ing
    -0.55
     CURLOPT
    -0.52
    越大
    -0.51
    acción
    -0.51
    setVerticalGroup
    -0.50
    esian
    -0.49
    POSITIVE LOGITS
     protoimpl
    0.66
    UserScript
    0.64
     논
    0.55
    LookAnd
    0.54
     насељу
    0.54
    InitVars
    0.52
    Packs
    0.51
    lofen
    0.51
    @[+][
    0.50
    Rujuakan
    0.49
    Activations Density 0.171%

    No Known Activations