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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 6724
    Prev
    Next
    INDEX
    Explanations

    complex structures and relationships within sentences

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

    references to specific actions and relationships among entities in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/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.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esternos
    -0.91
    mybatisplus
    -0.88
    IndentedString
    -0.82
    +#+#
    -0.79
    Rohy
    -0.76
     ویکی‌پدیای
    -0.76
    Jereo
    -0.75
    $_['
    -0.74
    وأضاف
    -0.72
    LLocation
    -0.70
    POSITIVE LOGITS
    MessageInfo
    0.47
    })()
    0.46
     people
    0.42
    ัย
    0.42
    ">(</
    0.41
     peop
    0.40
    ity
    0.40
     lös
    0.39
                                   
    0.38
     limited
    0.37
    Activations Density 0.795%

    No Known Activations