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 - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 396
    Prev
    Next
    INDEX
    Explanations

    concepts related to counterclaims and counterarguments in legal or analytical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wohnen
    -0.46
    Dreams
    -0.44
    OOTDTY
    -0.43
    medriver
    -0.43
     fhall
    -0.42
     Picchu
    -0.41
    dreaming
    -0.41
    cshtml
    -0.41
    MAPS
    -0.41
    BibitemShut
    -0.40
    POSITIVE LOGITS
     counter
    3.06
     Counter
    2.77
     COUNTER
    2.69
    counter
    2.69
    Counter
    2.55
     counters
    2.31
    COUNTER
    2.25
     Counters
    2.05
    Counters
    1.80
    counters
    1.76
    Activations Density 0.118%

    No Known Activations