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. 10-GEMMASCOPE-RES-16K
    6. 8327
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols related to statistical or probabilistic calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تانيه
    -0.63
    AccessorTable
    -0.60
     оригіналу
    -0.54
     shaw
    -0.54
     الرياضيه
    -0.53
    RTGC
    -0.52
    ConstraintMaker
    -0.52
     خاط
    -0.51
    脚注の使い方
    -0.50
     ITIS
    -0.49
    POSITIVE LOGITS
    ostí
    0.59
     StringTokenizer
    0.59
    pulumi
    0.57
    intios
    0.57
     Савезне
    0.56
     Gers
    0.52
    umentar
    0.51
    salsa
    0.50
    lineno
    0.50
    ManyToMany
    0.48
    Activations Density 1.006%

    No Known Activations