© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 1915
    Prev
    Next
    INDEX
    Explanations

    terms related to validation and errors in data processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.85
    +#+#
    -0.83
    ">—
    -0.67
     CreateTagHelper
    -0.67
    UserScript
    -0.64
    Os
    -0.63
    sonian
    -0.63
     bArr
    -0.63
     Burr
    -0.61
     CGSize
    -0.60
    POSITIVE LOGITS
     validation
    2.85
     validate
    2.70
     Validation
    2.68
    validation
    2.65
     Validate
    2.50
     validating
    2.47
    Validation
    2.43
    validate
    2.41
     validations
    2.40
     validates
    2.33
    Activations Density 0.031%

    No Known Activations