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. 19-GEMMASCOPE-RES-16K
    6. 11677
    Prev
    Next
    INDEX
    Explanations

    phrases related to roles and responsibilities, particularly in leadership and community contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    djangoproject
    -0.59
    TextChanged
    -0.49
     colored
    -0.48
    ETTA
    -0.47
    Indent
    -0.46
    Fort
    -0.46
    nend
    -0.46
    ixante
    -0.45
    colored
    -0.44
    éges
    -0.44
    POSITIVE LOGITS
     roles
    2.40
     role
    2.39
    role
    2.06
     Roles
    1.99
     Role
    1.99
    Role
    1.96
    roles
    1.93
     ROLE
    1.91
     rôle
    1.86
     rôles
    1.85
    Activations Density 0.222%

    No Known Activations