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. 18-GEMMASCOPE-RES-16K
    6. 3671
    Prev
    Next
    INDEX
    Explanations

    phrases related to web features and updates

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

    Preceding links or button actions

    np_acts-logits-general · gemini-2.0-flash

    click here

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.94
    ]")]
    -0.77
    ########.
    -0.75
    PyExc
    -0.71
    contentLoaded
    -0.66
     виправивши
    -0.65
    +:+
    -0.62
    出版年
    -0.62
    nonatomic
    -0.61
    GraphicsUnit
    -0.61
    POSITIVE LOGITS
     click
    1.87
     Click
    1.77
     CLICK
    1.71
    Click
    1.64
    click
    1.57
     HERE
    1.55
    CLICK
    1.51
     clicking
    1.44
     here
    1.41
     klik
    1.28
    Activations Density 0.426%

    No Known Activations