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. 209
    Prev
    Next
    INDEX
    Explanations

    concepts related to self-awareness and critical thinking about social roles and information dissemination

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

    language about information literacy, media consumption, and understanding how information is produced and spread.

    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
     يتيمه
    -0.60
     للاسماء
    -0.55
    +#+#
    -0.54
     intStringLen
    -0.54
    itinéraire
    -0.53
    تفصیلات
    -0.52
    TestBed
    -0.52
     Bioaccumulative
    -0.49
     său
    -0.49
     ecran
    -0.49
    POSITIVE LOGITS
     understanding
    0.45
     how
    0.45
     awareness
    0.44
     why
    0.42
     recognizes
    0.42
     recognizing
    0.41
     critical
    0.39
     realizes
    0.38
     recognize
    0.38
     sees
    0.37
    Activations Density 0.168%

    No Known Activations