© 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. 7354
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation marks and sentence beginnings

    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
    ↵↵
    -1.84
    ↵
    -1.10
    ↵↵↵
    -1.09
    </h3>
    -0.93
    ↵↵↵↵
    -0.81
    ↵↵↵↵↵
    -0.80
    </h4>
    -0.77
    <eos>
    -0.75
    </blockquote>
    -0.74
    ↵↵↵↵↵↵↵
    -0.73
    POSITIVE LOGITS
     كومونز
    0.76
    GraphicsUnit
    0.71
    Vidite
    0.67
     newBuilder
    0.62
    TextAppearance
    0.61
    nmgp
    0.60
    umenical
    0.60
    copg
    0.58
    eneuve
    0.58
    HostException
    0.57
    Activations Density 0.558%

    No Known Activations