© 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. 21-GEMMASCOPE-RES-16K
    6. 8748
    Prev
    Next
    INDEX
    Explanations

    phrases related to the management and exploitation of Michael Jackson's legacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -1.12
     disambiguazione
    -1.01
    ItemBackground
    -0.89
    InitVars
    -0.85
    دانشنامهٔ
    -0.81
    CppCodeGen
    -0.80
    DockStyle
    -0.80
     HasFactory
    -0.79
     समीक्षाओं
    -0.75
     "..\..\..\
    -0.73
    POSITIVE LOGITS
    浮
    0.48
    vro
    0.48
    anyak
    0.48
    みましょう
    0.47
    tetra
    0.45
     Carbon
    0.44
    niad
    0.44
    Svc
    0.44
     tetra
    0.43
    jsko
    0.43
    Activations Density 0.193%

    No Known Activations