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. 8898
    Prev
    Next
    INDEX
    Explanations

    references to digital trends and language related to technology and social dynamics

    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
    PerformLayout
    -0.61
    sidian
    -0.56
     незавершена
    -0.55
     داشتند
    -0.54
     gehad
    -0.53
    providedIn
    -0.53
     المعيارى
    -0.51
    PYX
    -0.51
    Демографія
    -0.50
    aarrggbb
    -0.50
    POSITIVE LOGITS
     become
    2.98
     becomes
    2.76
    become
    2.56
     became
    2.55
     becoming
    2.55
     Become
    2.53
    becomes
    2.36
     Becomes
    2.35
    Become
    2.27
     BECOME
    2.25
    Activations Density 0.669%

    No Known Activations