© 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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 13833
    Prev
    Next
    INDEX
    Explanations

    code involving the manipulation of data structures, particularly vectors and arrays

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

    Code-related syntax

    np_acts-logits-general · gemini-2.0-flash

    code structure initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =!
    -0.56
     PyObject
    -0.51
    AddHtmlAttribute
    -0.50
    =@"
    -0.48
     who
    -0.47
    clusão
    -0.46
     ๆ
    -0.45
     कैसी
    -0.44
    astero
    -0.44
    似的
    -0.44
    POSITIVE LOGITS
     {-
    0.68
    {-
    0.63
    make
    0.63
    makeText
    0.59
     CreateTagHelper
    0.59
    IVEREF
    0.58
    rungsseite
    0.58
     make
    0.57
     Vector
    0.56
    Make
    0.55
    Activations Density 0.254%

    No Known Activations