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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 7133
    Prev
    Next
    INDEX
    Explanations

    terms related to methods and methodologies

    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
     Efq
    -1.29
     HasFactory
    -1.03
    sizeCache
    -1.00
     ESR
    -0.99
     poffible
    -0.97
     zir
    -0.97
     poffe
    -0.95
     myſelf
    -0.94
     Monfieur
    -0.94
     cuck
    -0.93
    POSITIVE LOGITS
     methods
    1.27
     Method
    1.22
    getMethod
    1.21
     Methods
    1.21
    methods
    1.18
     method
    1.14
    METHOD
    1.14
    Method
    1.13
     METHOD
    1.13
    method
    1.11
    Activations Density 0.065%

    No Known Activations