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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 13195
    Prev
    Next
    INDEX
    Explanations

    occurrences of memory allocation functions in programming contexts

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

    c memory allocation functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.51
     Nina
    -0.41
    Ender
    -0.41
     Audiodateien
    -0.41
     Seelen
    -0.40
     oppose
    -0.40
     Cassandra
    -0.40
    JsonHelper
    -0.39
     Piper
    -0.39
    Sik
    -0.39
    POSITIVE LOGITS
    malloc
    3.09
     malloc
    2.33
    Malloc
    1.63
    calloc
    1.17
    realloc
    1.07
     calloc
    0.96
    stdlib
    0.93
     ALLOC
    0.74
    strdup
    0.73
     Alloc
    0.70
    Activations Density 0.001%

    No Known Activations