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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2041
    Prev
    Next
    INDEX
    Explanations

    HTML heading tags and their attributes

    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
    TagMode
    -0.86
    исленность
    -0.85
    ContentAsync
    -0.71
     ddelweddau
    -0.68
    Enllaces
    -0.67
    ietal
    -0.63
    TypedDataSet
    -0.62
    ")->
    -0.59
    θρω
    -0.59
     دیکھیے
    -0.58
    POSITIVE LOGITS
    <h4>
    0.66
    imageshack
    0.57
    }*/
    0.56
    __*/
    0.54
     esegu
    0.52
    openSession
    0.47
     ricordo
    0.47
     ricordi
    0.46
    انيف
    0.46
    </h3>
    0.46
    Activations Density 0.039%

    No Known Activations