© 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. 18-GEMMASCOPE-RES-16K
    11. 419
    Prev
    Next
    INDEX
    Explanations

    references to specific dates and events

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

    Text following a period

    np_acts-logits-general · gemini-2.0-flash

    only one

    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
     ‘
    -0.78
    </em>
    -0.78
     “
    -0.76
    …”
    -0.68
    ,”
    -0.65
    …
    -0.64
    ”
    -0.62
    </h5>
    -0.62
     
    -0.61
    <strong>
    -0.61
    POSITIVE LOGITS
    <table>
    0.86
     wikipagina
    0.75
    ${\
    0.71
    fromnode
    0.63
     NgModule
    0.63
     BNF
    0.62
    balleur
    0.61
     GenerationType
    0.60
     opium
    0.59
     Antara
    0.59
    Activations Density 0.245%

    No Known Activations