© 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. 2-GEMMASCOPE-RES-16K
    6. 1982
    Prev
    Next
    INDEX
    Explanations

    terms related to inventions and methods in technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bewerken
    -0.55
    Personendaten
    -0.51
    XtraReports
    -0.48
    명
    -0.47
     Heartland
    -0.45
     mergeFrom
    -0.45
    PRWEB
    -0.44
     XCTest
    -0.43
    னை
    -0.43
     flexibility
    -0.42
    POSITIVE LOGITS
    CopyWith
    0.66
    клопе
    0.65
    脚注の使い方
    0.65
     LIRE
    0.63
     abon
    0.60
    tonode
    0.58
    ائص
    0.58
    dflare
    0.57
    orsing
    0.57
    andExpect
    0.56
    Activations Density 1.100%

    No Known Activations