© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 6921
    Prev
    Next
    INDEX
    Explanations

    graphical representations and figures in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    File names in image tags

    np_acts-logits-general · gemini-2.0-flash

    image references and figure numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -1.02
     itſelf
    -1.02
    OGND
    -0.86
    complexContent
    -0.85
     Houſe
    -0.83
    kháu
    -0.83
    enumi
    -0.82
     Мексичка
    -0.81
    WarningLevel
    -0.81
     незавершена
    -0.81
    POSITIVE LOGITS
    <eos>
    0.84
    ↵↵
    0.75
    \\
    0.69
    ↵
    0.65
    ↵↵↵
    0.65
    ↵↵↵↵
    0.62
    ↵↵↵↵↵
    0.51
    ↵↵↵↵↵↵
    0.48
    ꒳
    0.48
    .\\
    0.48
    Activations Density 0.342%

    No Known Activations