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. 10685
    Prev
    Next
    INDEX
    Explanations

    references to the authority and recognition of religious leaders and their teachings

    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
     مرئيه
    -0.62
     Kombin
    -0.52
     engineers
    -0.52
     Ingenie
    -0.51
     Zool
    -0.51
     Engineers
    -0.49
     engineer
    -0.48
     bragging
    -0.48
     engineering
    -0.48
     game
    -0.47
    POSITIVE LOGITS
    MessageOf
    0.91
    XmlEnum
    0.68
    tagext
    0.65
    Lähteet
    0.64
    ⓧ
    0.63
     geldig
    0.60
    ]-->
    0.60
    rrggbb
    0.59
    AndEndTag
    0.58
    StoryboardSegue
    0.57
    Activations Density 0.322%

    No Known Activations