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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-GEMMASCOPE-RES-16K
    6. 2295
    Prev
    Next
    INDEX
    Explanations

    references to sequels, prequels, and interconnected storytelling within series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.95
    IntoConstraints
    -0.91
    ItemBackground
    -0.85
    BagConstraints
    -0.84
    __*/
    -0.83
    ynb
    -0.81
     FetchType
    -0.81
    PMailer
    -0.81
    astify
    -0.78
    RuleContext
    -0.78
    POSITIVE LOGITS
     series
    0.64
    series
    0.50
     length
    0.45
    neurs
    0.45
    zana
    0.43
    логі
    0.42
     fan
    0.42
    fan
    0.42
     world
    0.42
    story
    0.41
    Activations Density 0.202%

    No Known Activations