© 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. 5-GEMMASCOPE-RES-16K
    11. 7657
    Prev
    Next
    INDEX
    Explanations

    phrases indicating approximate quantities or ranges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oplayer
    -0.53
     ‘
    -0.50
    ’
    -0.50
    moveToNext
    -0.49
     and
    -0.49
     the
    -0.49
     multiple
    -0.49
     –
    -0.48
    !
    -0.48
    </b>
    -0.47
    POSITIVE LOGITS
     roughly
    1.13
     Roughly
    1.05
     ungefähr
    1.03
    awtextra
    1.03
     ungefär
    1.02
     aproximado
    0.98
     approx
    0.97
    Bout
    0.95
     aproximativ
    0.93
     etwa
    0.92
    Activations Density 0.133%

    No Known Activations