© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 99598
    Prev
    Next
    INDEX
    Explanations

    the character "<" followed by a non-zero activation value, likely indicating a focus on template or type specifications in programming

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

    code structures and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.77
    AddTagHelper
    -0.57
    ImageIO
    -0.57
    ,$_
    -0.57
    URLException
    -0.56
    AndroidJUnit
    -0.56
     ioutil
    -0.54
    serviceWorker
    -0.53
    featureID
    -0.51
     Erle
    -0.51
    POSITIVE LOGITS
    <
    1.15
     <
    0.77
    }<
    0.68
    ()<
    0.66
    ]<
    0.65
    ><
    0.62
    _<
    0.62
    :<
    0.61
    《
    0.60
    )<
    0.59
    Activations Density 0.011%

    No Known Activations