© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 10991
    Prev
    Next
    INDEX
    Explanations

    programming constructs and function calls related to building and adding components in code

    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
     дописавши
    -0.60
     Савезне
    -0.58
     TextAppearance
    -0.58
     titolata
    -0.57
     Италијани
    -0.56
    <bos>
    -0.54
    InitVars
    -0.53
     ovp
    -0.52
     gustaba
    -0.52
     oprot
    -0.51
    POSITIVE LOGITS
     wireType
    0.67
     مواليد
    0.63
    などなど
    0.63
     etc
    0.61
    MockMvc
    0.59
     usw
    0.57
    OrNil
    0.56
     …
    0.55
    Javadoc
    0.54
    etc
    0.54
    Activations Density 0.391%

    No Known Activations