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. 5-GEMMASCOPE-RES-16K
    6. 7105
    Prev
    Next
    INDEX
    Explanations

    the term "joint" in various contexts, particularly in legal and medical discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cadora
    -0.72
    ergies
    -0.69
    rxjs
    -0.68
     gtk
    -0.68
     papá
    -0.66
    andExpect
    -0.66
    jillo
    -0.64
    емость
    -0.63
     Hager
    -0.63
     occhiali
    -0.62
    POSITIVE LOGITS
     joint
    2.17
     Joint
    2.16
    joint
    2.08
     JOINT
    2.07
    Joint
    2.07
     Joints
    2.03
     joints
    1.97
    JOINT
    1.80
    joints
    1.74
     jointly
    1.33
    Activations Density 0.039%

    No Known Activations