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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 1082
    Prev
    Next
    INDEX
    Explanations

    words related to scientific reporting and research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    statements starting clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    帖最后由
    -0.86
    httphttps
    -0.84
    +#+#
    -0.82
     يتيمه
    -0.79
    bootstrapcdn
    -0.78
    StoryboardSegue
    -0.75
    下载附件
    -0.74
    OGND
    -0.74
    Попис
    -0.73
     snippetHide
    -0.73
    POSITIVE LOGITS
    ↵
    0.38
    <eos>
    0.35
    1
    0.31
    #
    0.31
    E
    0.28
     
    0.28
    This
    0.28
    Health
    0.28
    2
    0.28
     …
    0.27
    Activations Density 0.653%

    No Known Activations