© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 14609
    Prev
    Next
    INDEX
    Explanations

    Java programming constructs, particularly involving BigInteger and bit manipulation

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

    Hexadecimal values or bitwise operations

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal max values and bitmasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.71
     esterni
    -0.67
    ngdoc
    -0.58
     esternos
    -0.53
    Composable
    -0.52
    Einzelnachweise
    -0.51
     Joi
    -0.49
    tanleria
    -0.48
     lay
    -0.48
    qtype
    -0.47
    POSITIVE LOGITS
    MaxValue
    0.74
     UINT
    0.74
     MAX
    0.72
    MAX
    0.70
     maxValue
    0.70
    Max
    0.65
     FFFF
    0.65
    maxValue
    0.64
     Max
    0.63
     max
    0.62
    Activations Density 0.294%

    No Known Activations