© 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. 2-GEMMASCOPE-RES-16K
    6. 7055
    Prev
    Next
    INDEX
    Explanations

    phrases and clauses related to the concept of "deletion" and "properties" in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Audiodateien
    -0.64
    первых
    -0.62
    Gilla
    -0.61
    arity
    -0.60
    makeConstraints
    -0.58
    fuj
    -0.57
     AssemblyCompany
    -0.56
    ::__
    -0.56
    Ecco
    -0.56
    这两
    -0.54
    POSITIVE LOGITS
     Gher
    0.72
     Shand
    0.71
    igraphy
    0.65
     Negeri
    0.64
    robial
    0.63
    Hochspringen
    0.63
    Eyed
    0.63
     Banten
    0.62
     setName
    0.61
     σε
    0.60
    Activations Density 0.076%

    No Known Activations