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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 11186
    Prev
    Next
    INDEX
    Explanations

    formal programming syntax elements

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

    Code related to integers

    np_acts-logits-general · gemini-2.0-flash

    integer values and types

    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
     Excess
    -0.47
    вър
    -0.47
     Reverso
    -0.43
    <bos>
    -0.42
     vieja
    -0.40
    sslich
    -0.40
    īj
    -0.39
     предъ
    -0.38
    unjang
    -0.38
     hjälp
    -0.38
    POSITIVE LOGITS
     int
    2.43
    int
    2.33
     Int
    1.35
    Int
    1.30
    INT
    1.21
     INT
    1.19
     ints
    1.19
    ∫
    1.18
     integer
    1.08
    intar
    1.02
    Activations Density 0.204%

    No Known Activations