© 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. 23-GEMMASCOPE-RES-16K
    6. 14686
    Prev
    Next
    INDEX
    Explanations

    technical terms and classes related to programming, particularly in Java and Android development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    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
    -0.88
     المعيارى
    -0.74
     تانيه
    -0.70
     Administrativna
    -0.69
    MessageState
    -0.68
    __(/*!
    -0.67
    下载附件
    -0.67
    ----</
    -0.66
    enterOuterAlt
    -0.66
    #
    -0.65
    POSITIVE LOGITS
     my
    0.60
    Impl
    0.52
     builder
    0.51
     protoimpl
    0.51
     a
    0.50
    Builder
    0.48
    cibility
    0.46
     o
    0.46
     _
    0.45
     m
    0.44
    Activations Density 0.201%

    No Known Activations