© 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. 4-GEMMASCOPE-RES-16K
    11. 931
    Prev
    Next
    INDEX
    Explanations

    phrases indicating composition or structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kuuta
    -0.64
     argint
    -0.58
    droje
    -0.55
    TintMode
    -0.54
    saraba
    -0.53
    DialogTitle
    -0.53
    theless
    -0.51
     CiNii
    -0.51
    Tikang
    -0.50
    margins
    -0.50
    POSITIVE LOGITS
     comprised
    1.40
     consists
    1.35
     consisted
    1.29
     comprising
    1.27
     comprises
    1.25
     consisting
    1.25
     consist
    1.25
     gồm
    1.19
     terdiri
    1.16
     comprise
    1.12
    Activations Density 0.287%

    No Known Activations