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. 14-GEMMASCOPE-RES-16K
    6. 100
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to proving claims and establishing evidence

    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
    fjspx
    -0.79
    URLException
    -0.75
     ―――――
    -0.67
     IBOutlet
    -0.65
    réhen
    -0.65
    
    -0.63
    UserScript
    -0.62
    yntaxException
    -0.61
    SPJ
    -0.61
    QUIR
    -0.61
    POSITIVE LOGITS
     proof
    1.13
     prove
    1.12
     prouve
    1.07
     proves
    1.06
     proving
    1.06
     proofs
    1.03
     prouver
    1.01
    证明
    1.00
     preuves
    0.99
     demostrar
    0.99
    Activations Density 0.803%

    No Known Activations