© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 4109
    Prev
    Next
    INDEX
    Explanations

    references to technological constructs and their functionality

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    about projecting or emerging from something

    np_acts-logits-general · gemini-2.0-flash

    shoot from

    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
    Negative Logits
     }}{
    -0.48
    }}{
    -0.45
    sol
    -0.42
     sol
    -0.41
    味
    -0.40
    Application
    -0.40
    base
    -0.40
    omer
    -0.39
    dol
    -0.38
    קל
    -0.38
    POSITIVE LOGITS
     emanating
    1.05
     emerge
    0.99
     sprouting
    0.95
     emerging
    0.94
     Emerging
    0.86
     emergence
    0.85
     emerged
    0.85
     emerges
    0.84
     protruding
    0.84
     sprout
    0.82
    Activations Density 0.287%

    No Known Activations