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. 14-GEMMASCOPE-RES-16K
    6. 2925
    Prev
    Next
    INDEX
    Explanations

    phrases related to long-term plans and aspirations

    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
     فريبيس
    -0.54
    saraba
    -0.49
    ða
    -0.47
     voud
    -0.46
    قایناقلار
    -0.46
    coles
    -0.46
    hver
    -0.45
    นาน
    -0.44
    deelte
    -0.41
    ynchrotron
    -0.40
    POSITIVE LOGITS
     Roskov
    1.00
     aforesaid
    0.70
    mentioned
    0.68
    OGND
    0.62
     above
    0.61
     mentioned
    0.61
     aforementioned
    0.61
    onActivityResult
    0.60
     kaarangay
    0.59
     Mentioned
    0.59
    Activations Density 0.971%

    No Known Activations