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. 4061
    Prev
    Next
    INDEX
    Explanations

    programming concepts related to data structures and operations in JavaScript

    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
     herself
    -1.26
     she
    -1.17
    she
    -0.95
    She
    -0.90
    herself
    -0.89
     koja
    -0.87
     która
    -0.83
     She
    -0.81
     која
    -0.80
     została
    -0.75
    POSITIVE LOGITS
     himself
    0.60
    ът
    0.44
    Completo
    0.42
     completo
    0.42
    lowns
    0.41
     tecnológico
    0.41
    cito
    0.41
     vårt
    0.41
     nostru
    0.41
     definitivo
    0.40
    Activations Density 0.066%

    No Known Activations