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. 2-GEMMASCOPE-RES-16K
    6. 15225
    Prev
    Next
    INDEX
    Explanations

    keywords related to state management and user interactions in a programming context

    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
    Bronnen
    -0.59
    Източници
    -0.57
    \}^{
    -0.52
    chila
    -0.51
    ettbewer
    -0.49
    Eph
    -0.49
    hrter
    -0.47
    ]<=
    -0.46
     poils
    -0.46
     menyus
    -0.46
    POSITIVE LOGITS
     consultato
    0.80
    rrggbb
    0.68
     favourites
    0.66
     Reichstag
    0.64
     DBNull
    0.62
    PrototypeOf
    0.61
    +#+#
    0.61
    ----</
    0.60
    EDEFAULT
    0.60
     Pyrene
    0.59
    Activations Density 0.807%

    No Known Activations