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. 6096
    Prev
    Next
    INDEX
    Explanations

    programming language syntax and structure, particularly for Java

    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
    ChildScrollView
    -0.60
     مشين
    -0.58
     препратки
    -0.57
     pcs
    -0.57
     noqa
    -0.53
    scriptcase
    -0.53
    ViewFeatures
    -0.51
    databind
    -0.50
    extAlignment
    -0.49
     PC
    -0.49
    POSITIVE LOGITS
     Савезне
    0.89
    RegistryLite
    0.72
     HasFactory
    0.72
    esez
    0.67
     argint
    0.65
     kaarangay
    0.61
    Aholisi
    0.61
     piele
    0.61
    uelan
    0.58
     pauvres
    0.58
    Activations Density 0.060%

    No Known Activations