Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 6695
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and structural elements in equations

    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
    ↵↵
    -0.86
    ↵↵↵
    -0.76
    ness
    -0.74
    ↵↵↵↵↵
    -0.72
    ↵↵↵↵↵↵
    -0.68
    <eos>
    -0.66
    )—
    -0.63
    ↵
    -0.63
    ↵↵↵↵
    -0.62
     Del
    -0.60
    POSITIVE LOGITS
    +#+#
    1.15
     rendus
    0.93
    httphttps
    0.90
    gdx
    0.89
    couvrez
    0.88
     suivante
    0.81
    tvguidetime
    0.81
    帖最后由
    0.80
    ẫ
    0.80
     sinned
    0.79
    Activations Density 0.428%

    No Known Activations