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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53376
    Prev
    Next
    INDEX
    Explanations

    components of film reviews

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

    review or rating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الدولى
    -0.56
    ワイイ
    -0.47
     Dernière
    -0.47
     ArrayAdapter
    -0.46
    FieldDescriptor
    -0.46
    icrous
    -0.46
     mắn
    -0.45
    jacency
    -0.45
    ASX
    -0.45
    herin
    -0.44
    POSITIVE LOGITS
     review
    1.40
     reviews
    1.28
     reviewers
    1.21
     reviewer
    1.19
    review
    1.19
     reviewing
    1.18
     rating
    1.16
     Review
    1.12
    Review
    1.11
    reviews
    1.11
    Activations Density 0.376%

    No Known Activations