© 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. 3637
    Prev
    Next
    INDEX
    Explanations

    code structure elements and attributes related to API functionality

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

    Followed by parentheses

    np_acts-logits-general · gemini-2.0-flash

    Rust and C# code 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
     OFDb
    -0.48
    CESO
    -0.46
    JsonHelper
    -0.46
    TestingModule
    -0.45
     punches
    -0.43
    undle
    -0.43
    opsis
    -0.42
     Great
    -0.42
    jooq
    -0.42
     Tind
    -0.41
    POSITIVE LOGITS
    SourceChecksum
    0.73
     ModelExpression
    0.69
    ]")]
    0.69
    Zeneca
    0.68
    tvguidetime
    0.68
     BorderSide
    0.65
    Attribute
    0.64
    +#+#
    0.63
     ComVisible
    0.63
    ंदीखरीदारी
    0.62
    Activations Density 0.105%

    No Known Activations