Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-GEMMASCOPE-RES-16K
    6. 13896
    Prev
    Next
    INDEX
    Explanations

    references to mathematical constructs and formal definitions involving pairs and settings in a structured format

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

    Mathematical pairs/tuples

    np_acts-logits-general · gemini-2.0-flash

    pairs, triplets, and tuples

    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
    expandindo
    -0.55
    <?=
    -0.43
    XtraEditors
    -0.42
    ifrance
    -0.42
    GLOBALS
    -0.42
     regionales
    -0.41
     kiệm
    -0.41
     ErrInvalid
    -0.40
    queryInterface
    -0.39
     misteriosa
    -0.39
    POSITIVE LOGITS
    =(
    1.22
     tuple
    1.16
    tuple
    1.13
     Tuple
    1.06
     =(
    1.03
    }=(
    1.02
    Tuple
    1.02
     $(
    0.99
    <(
    0.97
     }(
    0.97
    Activations Density 0.528%

    No Known Activations