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. 4304
    Prev
    Next
    INDEX
    Explanations

    technical terms and attributes related to software assembly and configuration

    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
    minecraft
    -0.49
     A
    -0.49
     ام
    -0.44
     P
    -0.43
     R
    -0.41
     
    -0.41
     Hol
    -0.41
    isBlank
    -0.41
     Ho
    -0.41
     modo
    -0.41
    POSITIVE LOGITS
    InjectAttribute
    4.50
    IsContent
    2.59
     ModelExpression
    2.26
     defaultstate
    2.15
     ComVisible
    2.10
    ISupport
    2.09
    ftagPool
    2.07
    awtextra
    1.97
     AssemblyCulture
    1.96
     AssemblyVersion
    1.86
    Activations Density 0.007%

    No Known Activations