Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10777
    Prev
    Next
    INDEX
    Explanations

    terms related to comparisons and relationships between entities, particularly in a contextual or experimental framework

    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
    SharedDtor
    -0.87
    AndEndTag
    -0.79
     كومونز
    -0.77
     Paglinawan
    -0.77
    InjectMocks
    -0.75
    LLocation
    -0.72
     fVar
    -0.72
     doubtnut
    -0.71
     pylint
    -0.71
     itſelf
    -0.71
    POSITIVE LOGITS
    <eos>
    0.52
    …
    0.51
     respective
    0.51
      
    0.49
     THAN
    0.47
    ಃ
    0.46
    isling
    0.46
     gynhyrchwyd
    0.45
     –
    0.45
     future
    0.45
    Activations Density 0.360%

    No Known Activations