© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 7796
    Prev
    Next
    INDEX
    Explanations

    objects and their attributes in a structured data format

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

    SQL queries and code snippets

    np_acts-logits-general · gemini-2.0-flash

    user identifiers and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     humaine
    -0.52
     culprits
    -0.49
     authors
    -0.48
     defendants
    -0.47
     perpetrators
    -0.47
    authors
    -0.46
     Authors
    -0.46
    ValueStyle
    -0.46
     recipients
    -0.46
     applicant
    -0.45
    POSITIVE LOGITS
     role
    0.91
     gender
    0.88
     roles
    0.86
     email
    0.84
     Role
    0.80
     hobbies
    0.78
    role
    0.77
     Roles
    0.77
     phone
    0.76
     ROLE
    0.76
    Activations Density 0.180%

    No Known Activations