© 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. 1748
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to programming, particularly in the context of software and data structures

    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
    Rujuakan
    -0.60
    LookAnd
    -0.60
     referenties
    -0.59
    хьтан
    -0.58
     candidates
    -0.58
    UserScript
    -0.58
     candidate
    -0.57
     становника
    -0.56
    findpost
    -0.56
    المشاركات
    -0.55
    POSITIVE LOGITS
    ep
    0.53
    Numeric
    0.52
    })));
    0.50
     prevalent
    0.49
    CWE
    0.48
     Ep
    0.48
    setState
    0.48
    Ep
    0.47
    esteem
    0.47
    nós
    0.47
    Activations Density 2.557%

    No Known Activations