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. 17-GEMMASCOPE-RES-16K
    6. 5217
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their relationships with others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VersionUID
    -0.66
     many
    -0.62
    findpost
    -0.62
     only
    -0.62
     very
    -0.59
    MockBean
    -0.58
    only
    -0.56
     juist
    -0.56
    mybatisplus
    -0.56
    則
    -0.56
    POSITIVE LOGITS
     imaginable
    1.02
     whatsoever
    0.96
     conceivable
    0.91
     jemals
    0.87
     slightest
    0.87
     ever
    0.83
    anything
    0.83
     Qualquer
    0.81
     anything
    0.78
     EVER
    0.77
    Activations Density 0.143%

    No Known Activations