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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 48
    Prev
    Next
    INDEX
    Explanations

    concepts related to social awareness and responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to personal awareness or collective reflection.

    oai_token-act-pair · gpt-4oTriggered by @neilrathi

    pronouns like "we", "our", and associated verbs that describe collective or shared experiences.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     original
    -0.40
     propOrder
    -0.38
    createNewFile
    -0.36
    ebenarnya
    -0.32
     belonged
    -0.31
     originales
    -0.31
     originale
    -0.31
    tiéndose
    -0.31
    Original
    -0.30
    belongs
    -0.30
    POSITIVE LOGITS
     ourselves
    1.27
     our
    0.85
     우리
    0.82
     máme
    0.79
     nossas
    0.79
     we
    0.75
     nossos
    0.73
    我们需要
    0.73
     nossa
    0.72
    我们的
    0.71
    Activations Density 0.315%

    No Known Activations