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. 1-GEMMASCOPE-RES-16K
    6. 6979
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of orientation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quæ
    -0.93
    出版年
    -0.76
    σιμοποι
    -0.71
    VolleyError
    -0.67
    Према
    -0.64
    qDebug
    -0.63
    raisemb
    -0.61
    czuk
    -0.60
     Infórmanos
    -0.60
     rodríguez
    -0.60
    POSITIVE LOGITS
     oriented
    1.43
     orientation
    1.40
    oriented
    1.31
     orient
    1.28
     minded
    1.26
    Oriented
    1.24
     mindset
    1.23
     Orientation
    1.21
     Oriented
    1.20
    orientation
    1.18
    Activations Density 0.067%

    No Known Activations