© 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. 9293
    Prev
    Next
    INDEX
    Explanations

    phrases related to methods for achieving objectives, particularly in scientific or technical contexts

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

    Need for a solution or method

    np_acts-logits-general · gemini-2.0-flash

    way to solve

    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
    TagMode
    -0.79
     autorytatywna
    -0.73
    IonicModule
    -0.70
     MaterialApp
    -0.69
    twimg
    -0.69
    TemporalType
    -0.69
     Мексичка
    -0.68
     ſeveral
    -0.67
    principalColumn
    -0.65
     ſever
    -0.64
    POSITIVE LOGITS
     reliable
    0.73
     preferably
    0.72
     somehow
    0.71
    +#+#
    0.69
     reliably
    0.66
    preferably
    0.65
     Preferably
    0.65
    能夠
    0.63
     Somehow
    0.63
     something
    0.60
    Activations Density 0.756%

    No Known Activations