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. 1-GEMMASCOPE-RES-16K
    6. 9884
    Prev
    Next
    INDEX
    Explanations

    references to console logging and error handling in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.77
    таратура
    -0.68
     poveznice
    -0.66
     فريبيس
    -0.63
    jsxFileName
    -0.60
    TargetException
    -0.59
    uitton
    -0.57
    zygous
    -0.53
     صوتيه
    -0.53
     "..\..\..\
    -0.52
    POSITIVE LOGITS
    va
    0.75
    Genre
    0.74
    VA
    0.72
     Genre
    0.72
    setopt
    0.70
    enumi
    0.68
     genre
    0.66
    脚注の使い方
    0.64
     genres
    0.64
    Print
    0.60
    Activations Density 0.098%

    No Known Activations