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. 11-GEMMASCOPE-RES-16K
    6. 1967
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and operations related to functions and sets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.60
    сылкі
    -0.58
    DebuggerNonUser
    -0.55
    arki
    -0.49
    Filmografia
    -0.48
    нрави
    -0.48
    ')):
    -0.47
    LookAnd
    -0.47
     trous
    -0.46
     passt
    -0.46
    POSITIVE LOGITS
    webElementGuid
    0.66
    #+#
    0.65
    MessageTagHelper
    0.62
    antaine
    0.58
    :+:
    0.56
    keyColumn
    0.55
    GEBURTSDATUM
    0.54
    InputTagHelper
    0.51
    НИК
    0.50
     Référence
    0.50
    Activations Density 1.093%

    No Known Activations