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. 13-GEMMASCOPE-RES-16K
    6. 7405
    Prev
    Next
    INDEX
    Explanations

    specific phrases indicating formal introductions or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndGlobalSection
    -1.10
    脚注の使い方
    -1.07
     betweenstory
    -1.02
     <=",
    -1.00
     nahilalakip
    -0.99
     незавершена
    -0.95
    BufferException
    -0.94
    MigrationBuilder
    -0.94
    ValueStyle
    -0.91
    WriteBarrier
    -0.91
    POSITIVE LOGITS
     
    0.76
    .
    0.60
    </h2>
    0.59
     (
    0.58
    <eos>
    0.58
     a
    0.55
     l
    0.55
    </h3>
    0.53
    ...
    0.53
    ),
    0.52
    Activations Density 0.678%

    No Known Activations