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. 21-GEMMASCOPE-RES-16K
    6. 6719
    Prev
    Next
    INDEX
    Explanations

    references to materials, specifically stainless steel and fossil fuels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    y
    -1.07
    istani
    -0.55
    al
    -0.55
    k
    -0.54
    т
    -0.52
    ary
    -0.52
    st
    -0.51
    و
    -0.50
    ar
    -0.50
    ки
    -0.50
    POSITIVE LOGITS
     Roskov
    0.83
     tartalomajánló
    0.80
     ModelExpression
    0.74
    tvguidetime
    0.72
    disposing
    0.71
    MemoryWarning
    0.70
    Composable
    0.70
    #+#
    0.69
    ]=>
    0.68
    protoc
    0.68
    Activations Density 0.444%

    No Known Activations