© 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. 3254
    Prev
    Next
    INDEX
    Explanations

    different approaches or methodologies in various contexts

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

    "approach" or its variants

    np_acts-logits-general · gemini-2.0-flash

    types of approach

    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
    AutoField
    -0.59
     nakalista
    -0.53
    principalColumn
    -0.49
    ana
    -0.49
     Audiodateien
    -0.47
    hiasan
    -0.46
     sempurna
    -0.45
     dinas
    -0.44
     merve
    -0.44
     đời
    -0.44
    POSITIVE LOGITS
     approach
    2.70
    approach
    2.40
     Approach
    2.34
     APPROACH
    2.15
     approche
    2.13
    Approach
    2.13
     approaches
    1.98
     abordagem
    1.87
    approche
    1.85
     pendekatan
    1.79
    Activations Density 0.438%

    No Known Activations