Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 1199
    Prev
    Next
    INDEX
    Explanations

    instances of access modifiers in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ligiloj
    -0.58
    isation
    -0.57
    ization
    -0.56
    Ide
    -0.51
    ophe
    -0.50
    p
    -0.50
     cok
    -0.49
    ever
    -0.49
    agisse
    -0.49
    gnat
    -0.49
    POSITIVE LOGITS
    SBATCH
    0.98
     snippetHide
    0.93
    #+#
    0.87
    "):
    
    0.81
     Normdatei
    0.78
    enius
    0.76
    }`).
    0.75
     PCS
    0.74
    FunctionFlags
    0.74
     Ewing
    0.73
    Activations Density 0.021%

    No Known Activations