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. 5-GEMMASCOPE-RES-16K
    6. 16249
    Prev
    Next
    INDEX
    Explanations

    negations in code or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    positiva
    -0.51
     podí
    -0.47
    BeNil
    -0.46
     talál
    -0.44
    uksessa
    -0.43
    มือ
    -0.43
    ArgumentParser
    -0.43
     Goodwill
    -0.43
    MILLIS
    -0.42
    __(/*!
    -0.42
    POSITIVE LOGITS
    stdc
    0.88
    BrowserModule
    0.82
    issau
    0.75
    testify
    0.75
    belline
    0.73
    MarshalTo
    0.71
    scalatest
    0.70
    帖最后由
    0.70
     Administrativna
    0.69
    phrine
    0.69
    Activations Density 0.041%

    No Known Activations