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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 8343
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to technology and intellectual property

    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
    таратура
    -0.83
     Constitucional
    -0.71
    toMatchSnapshot
    -0.69
    sizeCache
    -0.68
     ChromeDriver
    -0.67
     administrativos
    -0.65
    ,
    -0.64
    стероид
    -0.64
    nezeu
    -0.60
    NullCheck
    -0.59
    POSITIVE LOGITS
    RenderAtEndOf
    0.80
     ?',
    0.78
    "</
    0.76
     '</
    0.76
    '</
    0.75
     "</
    0.74
    ReusableCell
    0.73
    }$_
    0.73
     ?",
    0.73
     *++
    0.73
    Activations Density 1.722%

    No Known Activations