© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 12701
    Prev
    Next
    INDEX
    Explanations

    terms related to "compilation" and "complicated" concepts or processes

    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
    iksa
    -0.74
    EndTag
    -0.68
     Lec
    -0.68
     برانيه
    -0.67
    LayoutStyle
    -0.66
    Παραπομπές
    -0.66
    RCT
    -0.66
    
    -0.66
    (!__
    -0.65
     Lag
    -0.65
    POSITIVE LOGITS
    COM
    1.20
     KOM
    1.13
     COM
    1.11
    COMP
    1.04
    Com
    1.01
     commis
    1.00
     Compton
    1.00
     kom
    0.99
    Comp
    0.98
     COMP
    0.98
    Activations Density 0.167%

    No Known Activations