© 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. 22-GEMMASCOPE-RES-16K
    11. 8119
    Prev
    Next
    INDEX
    Explanations

    code related to printing functions in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    LLVM-related code or instructions

    np_acts-logits-general · gemini-2.0-flash

    LLVM Assembly and Print

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.63
    ypeł
    -0.56
     seconded
    -0.52
     springfox
    -0.52
     serum
    -0.52
     Koy
    -0.52
     delimiter
    -0.51
     بيها
    -0.51
     tiara
    -0.50
    èvres
    -0.48
    POSITIVE LOGITS
     intptr
    0.68
    ReusableCell
    0.59
    ंदीखरीदारी
    0.59
    llvm
    0.56
    Personendaten
    0.56
     صوتيه
    0.55
     Instruction
    0.53
    Cyfarwyddwr
    0.52
    LLVM
    0.51
    phis
    0.51
    Activations Density 0.530%

    No Known Activations