© 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. 11282
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and certain short-format text features

    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
    ”]
    -0.66
    <bos>
    -0.64
     ?'
    -0.61
    "}>
    -0.57
    localctx
    -0.55
    thâu
    -0.55
    ”“
    -0.55
    .”)
    -0.54
    "")
    -0.52
    '}>
    -0.52
    POSITIVE LOGITS
     détru
    0.90
     morire
    0.87
     définiti
    0.79
     menac
    0.79
     détruit
    0.78
     danni
    0.78
     chré
    0.77
     quæ
    0.77
     espirituales
    0.76
     ennemis
    0.76
    Activations Density 1.050%

    No Known Activations