Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 3448
    Prev
    Next
    INDEX
    Explanations

    terms related to specific geographical and ethnic identifiers

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

    Follows uncommon character sequences

    np_acts-logits-general · gemini-2.0-flash

    technical and programming terms2. specific entities and names3. scientific literature fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pherals
    -0.46
     y
    -0.44
    Джерела
    -0.43
    ,‎
    -0.43
    readdir
    -0.42
    addWidget
    -0.41
    iausi
    -0.41
    onucleotide
    -0.41
     NOI
    -0.41
    QtCore
    -0.41
    POSITIVE LOGITS
    sky
    0.80
     surla
    0.70
     Normdatei
    0.66
    SKY
    0.64
     ſeveral
    0.60
     fubject
    0.60
     AppBundle
    0.59
    ական
    0.59
    crição
    0.59
     defStyleAttr
    0.58
    Activations Density 0.087%

    No Known Activations