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. 2-GEMMASCOPE-RES-16K
    6. 1149
    Prev
    Next
    INDEX
    Explanations

    phrases referring to the act of establishing or determining something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.63
     Mice
    -0.63
     I
    -0.61
    fcntl
    -0.57
     Y
    -0.57
     dare
    -0.57
     sou
    -0.56
     coils
    -0.56
     T
    -0.56
     dro
    -0.56
    POSITIVE LOGITS
     establish
    2.85
     established
    2.78
     Establish
    2.77
     establishment
    2.74
    establish
    2.69
     ESTABL
    2.65
    Establish
    2.65
    established
    2.63
     establishes
    2.62
     establishing
    2.62
    Activations Density 0.069%

    No Known Activations