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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 10035
    Prev
    Next
    INDEX
    Explanations

    conjunctions and modifiers that express contrast or opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erapeutics
    -0.62
    WriteLiteral
    -0.60
     smel
    -0.60
    AutoScale
    -0.60
    zaam
    -0.59
    édrale
    -0.59
     '\\;'
    -0.58
    ModelForm
    -0.56
    therosclerosis
    -0.55
     FLA
    -0.55
    POSITIVE LOGITS
     but
    1.20
     tetapi
    1.09
     But
    1.06
     namun
    1.05
    but
    0.98
    Tetapi
    0.98
     BUT
    0.94
    But
    0.92
     pero
    0.92
     tapi
    0.92
    Activations Density 0.205%

    No Known Activations