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. 11641
    Prev
    Next
    INDEX
    Explanations

    HTML attributes associated with data toggling and AJAX functionalities

    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
     مشين
    -1.10
    Personensuche
    -1.08
    RenderAtEndOf
    -1.06
     contextLoads
    -1.01
     étoit
    -1.01
     avoient
    -0.95
     Efq
    -0.91
     auroit
    -0.90
     Italijani
    -0.90
     DriverManager
    -0.89
    POSITIVE LOGITS
     initial
    0.60
     AS
    0.53
     lead
    0.52
    -
    0.51
     original
    0.51
    …
    0.51
    정
    0.50
    <strong>
    0.49
    initial
    0.49
    dri
    0.49
    Activations Density 0.047%

    No Known Activations