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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 33-GEMMASCOPE-RES-131K
    6. 65953
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "after" and related temporal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Autorisations
    -0.52
     Autorizaciones
    -0.49
    uminescence
    -0.46
    expandindo
    -0.44
     kasarigan
    -0.44
    MemoryWarning
    -0.43
    InstanceState
    -0.40
     jadx
    -0.40
    SpringRunner
    -0.40
    Последние
    -0.40
    POSITIVE LOGITS
     another
    0.61
    styleType
    0.60
     sweaty
    0.57
     painful
    0.54
     heartbreaking
    0.53
     bloody
    0.53
     gorgeous
    0.52
     agonizing
    0.52
    another
    0.51
     exhausting
    0.51
    Activations Density 0.007%

    No Known Activations