© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 935
    Prev
    Next
    INDEX
    Explanations

    mentions of systems and their implications on individuals or society

    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
     CommonModule
    -0.64
    Brainz
    -0.60
    原始内容存档于
    -0.53
    kirch
    -0.52
    ंदीखरीदारी
    -0.51
     verho
    -0.49
     StringTokenizer
    -0.49
    meyen
    -0.48
    Parameterized
    -0.47
    onicus
    -0.47
    POSITIVE LOGITS
     bestow
    0.61
     impart
    0.60
     bring
    0.60
     brings
    0.59
     apport
    0.59
     wrought
    0.59
     entail
    0.59
     engender
    0.59
    prefixer
    0.58
     imparts
    0.58
    Activations Density 0.302%

    No Known Activations