© 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. 14-GEMMASCOPE-RES-16K
    11. 4575
    Prev
    Next
    INDEX
    Explanations

    various forms of punctuation and formatting cues in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doubtnut
    -1.00
     pngtree
    -0.96
     Meksiku
    -0.93
     lowa
    -0.92
     Majefty
    -0.91
     Jefus
    -0.90
     itſelf
    -0.88
     photolibrary
    -0.87
     Pind
    -0.87
     DIB
    -0.86
    POSITIVE LOGITS
     –
    1.49
    ––––
    1.24
    ––
    1.10
    –
    1.03
    ര്‍
    1.03
    .’
    1.03
    ’.
    1.01
    راً
    0.99
    ায়
    0.99
    =”
    0.97
    Activations Density 0.121%

    No Known Activations