© 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. 17-GEMMASCOPE-RES-16K
    6. 4883
    Prev
    Next
    INDEX
    Explanations

    terms related to software and applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.78
    AxisAlignment
    -0.61
    afficheront
    -0.60
     rospy
    -0.58
    mapStateToProps
    -0.56
    SourceChecksum
    -0.54
     HasFactory
    -0.54
    JsonKey
    -0.53
     CreateTagHelper
    -0.52
    fastjson
    -0.51
    POSITIVE LOGITS
     software
    1.04
     logiciel
    0.91
     Software
    0.82
    software
    0.77
     logiciels
    0.75
     features
    0.73
     licenses
    0.71
     desktop
    0.70
     professionali
    0.70
     licencia
    0.70
    Activations Density 0.517%

    No Known Activations