Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 1047
    Prev
    Next
    INDEX
    Explanations

    elements related to configuration settings and options

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

    configuration files or settings

    np_acts-logits-general · gemini-2.0-flash

    configuration file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ActionResult
    -0.78
    Personensuche
    -0.76
    Kjelder
    -0.69
     RemoteException
    -0.69
     autorytatywna
    -0.66
     CreateTagHelper
    -0.66
     rendus
    -0.66
     rück
    -0.65
     userSchema
    -0.64
     comets
    -0.64
    POSITIVE LOGITS
     getConfig
    1.07
    Config
    1.04
     CONFIG
    1.03
     Config
    1.02
    config
    1.00
    getConfig
    0.98
    CONFIG
    0.96
     config
    0.95
    setConfig
    0.93
    getConfiguration
    0.91
    Activations Density 0.093%

    No Known Activations