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. 12581
    Prev
    Next
    INDEX
    Explanations

    terms related to materials and their physical properties in scientific contexts

    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
    SourceChecksum
    -0.71
    tagHelperRunner
    -0.66
    rungsseite
    -0.64
    BeginContext
    -0.64
     tartalomajánló
    -0.61
     Administrativna
    -0.60
    principalTable
    -0.52
    期刊论文
    -0.51
    část
    -0.50
    JspWriter
    -0.50
    POSITIVE LOGITS
     structure
    1.31
     morphology
    1.30
     topology
    1.24
     shape
    1.24
     configuration
    1.21
     geometry
    1.19
     arrangement
    1.15
     architecture
    1.15
     layout
    1.13
     anatomy
    1.06
    Activations Density 2.150%

    No Known Activations