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. 2839
    Prev
    Next
    INDEX
    Explanations

    phrases related to patents, investments, and scientific terms in research contexts

    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
    Rujuakan
    -0.61
     fieldNum
    -0.59
    ftagPool
    -0.59
    Jeografia
    -0.58
     &___
    -0.57
    TypedDataSet
    -0.57
     ExecuteAsync
    -0.54
    AutoScaleMode
    -0.53
    atoare
    -0.53
     calendriers
    -0.53
    POSITIVE LOGITS
     another
    3.41
    another
    3.11
    Another
    2.88
     Another
    2.85
     ANOTHER
    2.45
     ytterligare
    1.84
    อีก
    1.80
     otro
    1.80
    Otra
    1.76
    Otro
    1.69
    Activations Density 0.441%

    No Known Activations