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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-GEMMASCOPE-RES-16K
    6. 2786
    Prev
    Next
    INDEX
    Explanations

    elements related to coding and technical inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -1.20
    帖最后由
    -1.13
    MigrationBuilder
    -1.08
    Personendaten
    -1.03
    tanleria
    -0.97
    DeleteBehavior
    -0.95
     Administrativna
    -0.94
    ſt
    -0.91
     propOrder
    -0.90
     EClass
    -0.89
    POSITIVE LOGITS
     
    0.65
    ↵
    0.62
    ↵↵
    0.58
    </strong>
    0.52
     $\
    0.52
    <strong>
    0.52
    </h2>
    0.48
    </em>
    0.45
    <u>
    0.44
     r
    0.43
    Activations Density 2.769%

    No Known Activations