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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12834
    Prev
    Next
    INDEX
    Explanations

    punctuation and structural markers within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.69
     Normdatei
    -0.68
    RegressionTest
    -0.65
    Бележки
    -0.65
     CreateTagHelper
    -0.60
    CloseOperation
    -0.60
    Datuak
    -0.58
    errHandler
    -0.58
    ########.
    -0.58
     Administrativna
    -0.57
    POSITIVE LOGITS
    ValueGeneration
    0.51
    ⎧
    0.30
    исленность
    0.30
     Erwä
    0.29
    bentukan
    0.28
    ":[{
    0.28
    enderror
    0.27
     zví
    0.25
     erklär
    0.23
     sué
    0.23
    Activations Density 1.636%

    No Known Activations