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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 16185
    Prev
    Next
    INDEX
    Explanations

    critiques of character development or portrayal in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     setuptools
    -0.58
    wikimedia
    -0.55
     CreateTagHelper
    -0.54
     saites
    -0.53
     esternos
    -0.52
    Eksterne
    -0.49
    原始内容存档于
    -0.48
     ProtoMessage
    -0.48
     déclar
    -0.47
     geçti
    -0.46
    POSITIVE LOGITS
     annoying
    0.94
     annoy
    0.89
     irritating
    0.87
     annoys
    0.82
     Anno
    0.78
     bothers
    0.77
     annoyance
    0.76
     irritate
    0.75
     annoyed
    0.74
    PullParser
    0.70
    Activations Density 0.293%

    No Known Activations