© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 72343
    Prev
    Next
    INDEX
    Explanations

    error codes related to system calls in programming

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

    `syscall.Errno` with error codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Autorisations
    -0.67
    ፩
    -0.59
    WebVitals
    -0.54
     toured
    -0.54
    __':
    
    -0.53
     Columb
    -0.53
    ⓧ
    -0.53
     staged
    -0.52
     palettes
    -0.52
     dialogue
    -0.52
    POSITIVE LOGITS
    errno
    1.46
     errno
    1.17
    LastError
    0.69
     EINVAL
    0.47
     strerror
    0.47
    EINVAL
    0.44
    NSError
    0.41
     libc
    0.40
     errorCode
    0.37
     NSError
    0.37
    Activations Density 0.022%

    No Known Activations