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. 25-GEMMASCOPE-RES-16K
    6. 5750
    Prev
    Next
    INDEX
    Explanations

    terms related to support services and resources for victims of violence and related issues

    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
    IntoConstraints
    -0.72
    djangoproject
    -0.66
    Viited
    -0.60
     nakalista
    -0.60
    DrawerToggle
    -0.59
    ArgsConstructor
    -0.58
     transfieras
    -0.58
    ActionCreators
    -0.53
    rayage
    -0.52
    Profess
    -0.52
    POSITIVE LOGITS
     customers
    2.21
     users
    1.99
     consumers
    1.93
     Customers
    1.84
     clients
    1.81
     patients
    1.81
    Customers
    1.79
    customers
    1.76
     passengers
    1.66
     people
    1.66
    Activations Density 1.104%

    No Known Activations