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. 3-GEMMASCOPE-RES-16K
    6. 8291
    Prev
    Next
    INDEX
    Explanations

    terms related to "angiogenesis" and associated medical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.59
    RegressionTest
    -0.54
     Lietu
    -0.54
     Púb
    -0.54
     Bucure
    -0.53
     Sociales
    -0.53
    닙
    -0.53
    趣
    -0.53
     lửa
    -0.52
    desta
    -0.52
    POSITIVE LOGITS
    ang
    3.52
    ANG
    3.06
     ang
    2.30
    angs
    2.25
     Ang
    2.23
    Ang
    2.21
     ANG
    2.11
    angnya
    1.90
    angi
    1.79
    anga
    1.79
    Activations Density 0.076%

    No Known Activations