© 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
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1502
    Prev
    Next
    INDEX
    Explanations

    terms related to memory allocation and management in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -0.49
    ésultats
    -0.45
    ⓧ
    -0.45
    httphttps
    -0.45
    nextDouble
    -0.43
    izoen
    -0.42
    gridx
    -0.42
     invokingState
    -0.41
    arrings
    -0.40
    feinander
    -0.40
    POSITIVE LOGITS
    stdlib
    0.80
     malloc
    0.78
    malloc
    0.74
    realloc
    0.61
     calloc
    0.56
    calloc
    0.55
    kfree
    0.55
    cstdlib
    0.54
    ENOMEM
    0.54
    Malloc
    0.54
    Activations Density 0.225%

    No Known Activations