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. 1674
    Prev
    Next
    INDEX
    Explanations

    sections and references to theoretical algorithms and their evaluations in research 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
    delwed
    -0.67
    IntoConstraints
    -0.63
    ***********/
    -0.59
     Administrativna
    -0.52
    ⓧ
    -0.52
    oredCriteria
    -0.51
    XmlAccessorType
    -0.50
    Géographie
    -0.49
     Italijani
    -0.47
    vereignty
    -0.46
    POSITIVE LOGITS
     experiments
    0.81
     Experiments
    0.75
    Experiments
    0.71
     EXPERIMENTS
    0.70
     experimental
    0.67
     ablation
    0.66
     motivates
    0.66
     scalability
    0.66
     empirically
    0.65
    experiments
    0.64
    Activations Density 1.532%

    No Known Activations