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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 2968
    Prev
    Next
    INDEX
    Explanations

    functions related to object creation and initialization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (&:
    -0.76
    VersionUID
    -0.72
     onAnimation
    -0.72
    bmod
    -0.65
     jLabel
    -0.65
    BufferException
    -0.65
    PathVariable
    -0.64
    Personendaten
    -0.64
    ToMany
    -0.63
    CodedInputStream
    -0.63
    POSITIVE LOGITS
    create
    0.88
    Create
    0.79
    createNewFile
    0.72
     创建
    0.71
    CREATE
    0.71
     Create
    0.67
     cria
    0.67
     rosse
    0.66
     anew
    0.66
    ลิต
    0.65
    Activations Density 0.098%

    No Known Activations