© 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. 2968
    Prev
    Next
    INDEX
    Explanations

    variations of the word "approach" and related concepts

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

    "Approach" or similar word

    np_acts-logits-general · gemini-2.0-flash

    approach / approvals

    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
     tys
    -0.58
     Mur
    -0.57
     Rot
    -0.56
     Kar
    -0.56
     My
    -0.56
    Mur
    -0.54
     Tele
    -0.53
     Bur
    -0.53
     Super
    -0.53
    veyard
    -0.52
    POSITIVE LOGITS
     Monfieur
    1.00
     Approaches
    0.96
     approaches
    0.94
     itſelf
    0.93
     myſelf
    0.89
     Efq
    0.86
     pleaſure
    0.85
     auffi
    0.83
     uſed
    0.83
     APPROACH
    0.81
    Activations Density 0.122%

    No Known Activations