© 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. 25-GEMMASCOPE-RES-16K
    6. 6911
    Prev
    Next
    INDEX
    Explanations

    technical terms related to calculations and measurements in programming or 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
     ModelExpression
    -0.69
    Enllaces
    -0.59
    FormTagHelper
    -0.56
    Espèce
    -0.55
     UIKit
    -0.52
    DebuggerStep
    -0.52
     autorytatywna
    -0.51
     zvuky
    -0.51
     betweenstory
    -0.51
     Melch
    -0.48
    POSITIVE LOGITS
     min
    3.49
     Min
    3.38
    Min
    3.28
    min
    3.19
     MIN
    2.92
    MIN
    2.82
     minimum
    2.61
     getMin
    2.44
     Minimum
    2.42
    Minimum
    2.29
    Activations Density 0.600%

    No Known Activations