© 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. 2560
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology and concepts related to algebra and combinatorics

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

    Comes after "of", "a", "on", or "even"

    np_acts-logits-general · gemini-2.0-flash

    homogeneous polynomials of a certain type

    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
     الاطلاع
    -0.61
    rrggbb
    -0.53
    nocache
    -0.48
     >=",
    -0.44
     bambú
    -0.43
    ึ้น
    -0.43
     UIKit
    -0.43
     herencia
    -0.42
     mármol
    -0.42
    #+#
    -0.42
    POSITIVE LOGITS
    RectangleBorder
    0.65
    riwal
    0.58
    ngdoc
    0.57
     Hessen
    0.57
     weight
    0.55
     ballot
    0.54
     weights
    0.54
     समीक्षाएं
    0.54
    subpackage
    0.54
     bior
    0.53
    Activations Density 2.910%

    No Known Activations