© 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. 12656
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical properties and interactions of materials in various states and conditions

    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
    webElementXpaths
    -0.65
    AsUp
    -0.63
    rungsseite
    -0.62
     Obrador
    -0.58
     besoin
    -0.56
    sätzlich
    -0.55
    httphttps
    -0.54
     FormsModule
    -0.54
    providedIn
    -0.53
    .*")]
    -0.53
    POSITIVE LOGITS
     realistic
    0.61
     practical
    0.60
     gynhyrchwyd
    0.57
     realistically
    0.57
     arbitrarily
    0.57
     strongly
    0.56
     slowly
    0.55
     moderately
    0.53
     irregularly
    0.53
     crowded
    0.53
    Activations Density 1.417%

    No Known Activations