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. 2971
    Prev
    Next
    INDEX
    Explanations

    sentences conveying causal relationships and the implications of research findings

    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
     المعيارى
    -0.93
    httphttps
    -0.90
    MigrationBuilder
    -0.86
     thereof
    -0.83
     thereon
    -0.79
     فريبيس
    -0.77
    RectangleBorder
    -0.77
    Попис
    -0.75
     ddelweddau
    -0.74
     therefrom
    -0.74
    POSITIVE LOGITS
     the
    0.61
    ,
    0.60
     einerseits
    0.52
     las
    0.45
    ță
    0.45
     les
    0.44
    WireFormat
    0.44
     either
    0.44
    Източници
    0.43
     our
    0.43
    Activations Density 0.567%

    No Known Activations