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 - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 8666
    Prev
    Next
    INDEX
    Explanations

    the presence of apostrophes in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Demografie
    -0.59
    Conversely
    -0.53
    MigrationBuilder
    -0.49
    jména
    -0.48
    parsedMessage
    -0.48
    oredCriteria
    -0.48
     خارجية
    -0.47
    ьаж
    -0.46
    السكان
    -0.46
    ंदीखरीदारी
    -0.45
    POSITIVE LOGITS
    WaitGroup
    0.65
    MA
    0.59
    swire
    0.58
     oxidase
    0.58
    +:+
    0.55
    RS
    0.55
    therin
    0.55
    Ma
    0.54
    Portale
    0.54
    chu
    0.54
    Activations Density 0.128%

    No Known Activations