© 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. 8-GEMMASCOPE-RES-16K
    11. 15323
    Prev
    Next
    INDEX
    Explanations

    conjunctions and similar connecting phrases in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.76
    writeFieldEnd
    -0.70
    ysacchar
    -0.68
    ⓧ
    -0.59
     Thessalon
    -0.56
    bootstrapcdn
    -0.55
    onsored
    -0.55
    tonode
    -0.55
    Mixtures
    -0.55
     Preliminary
    -0.53
    POSITIVE LOGITS
     indeed
    0.54
     toki
    0.53
    Και
    0.52
     frankly
    0.51
     importantly
    0.50
    matchCondition
    0.50
     utafitiHapana
    0.49
     []:
    0.49
    osamente
    0.47
    順
    0.47
    Activations Density 0.258%

    No Known Activations