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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 7334
    Prev
    Next
    INDEX
    Explanations

    technical terms and definitions related to network protocols and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.69
    PerformLayout
    -0.67
    SourceChecksum
    -0.66
    AddTagHelper
    -0.59
    KommentareTeilen
    -0.58
     pulumi
    -0.56
    BeginInit
    -0.56
    Referanser
    -0.53
     kasarigan
    -0.52
    ंदीखरीदारी
    -0.52
    POSITIVE LOGITS
     UINT
    0.60
    (~
    0.57
    XtraGrid
    0.56
     ~
    0.56
     (~
    0.56
    ScopeManager
    0.55
    تقاوى
    0.55
     MAX
    0.52
    default
    0.51
    MaxValue
    0.50
    Activations Density 0.298%

    No Known Activations