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. 16-GEMMASCOPE-RES-16K
    6. 16115
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and functions related to memory allocation and management

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

    C/C++ buffer and array operations

    np_acts-logits-general · gemini-2.0-flash

    character buffer declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    openg
    -0.51
     nakalista
    -0.47
    men
    -0.44
    nox
    -0.44
     estekak
    -0.44
    Strict
    -0.44
    olin
    -0.43
     nguồn
    -0.43
     strict
    -0.42
    ренко
    -0.42
    POSITIVE LOGITS
     صوتيه
    0.66
     '\\;'
    0.66
     roomy
    0.64
    Jeografia
    0.63
     accomod
    0.60
     resourceCulture
    0.60
     disambiguazione
    0.59
     buffer
    0.59
    .*")]
    0.59
     समीक्षक
    0.59
    Activations Density 0.318%

    No Known Activations