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. 24-GEMMASCOPE-RES-16K
    6. 8114
    Prev
    Next
    INDEX
    Explanations

    terms related to genetics and cellular processes

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

    preceding suffixes or fragments

    np_acts-logits-general · gemini-2.0-flash

    legal and technical terms

    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
    IUrlHelper
    -0.64
    NameInMap
    -0.54
    <eos>
    -0.52
    воло
    -0.48
    byg
    -0.44
    </i>
    -0.43
    splitlines
    -0.42
    Географи
    -0.42
     fís
    -0.40
     disambiguazione
    -0.40
    POSITIVE LOGITS
    ActionCreators
    1.01
    ScopeManager
    0.90
    mybatisplus
    0.84
     विश्वसनीयता
    0.83
    MockBean
    0.77
    MessageTagHelper
    0.71
     AspNetCore
    0.71
    protoimpl
    0.71
     propOrder
    0.69
    CONSIN
    0.69
    Activations Density 0.818%

    No Known Activations