© 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. 2358
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific and technical references

    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
     makl
    -0.60
    setBold
    -0.57
    GOTREF
    -0.52
    quién
    -0.49
     thicker
    -0.49
     bawat
    -0.49
    govine
    -0.49
     proprement
    -0.48
    akteur
    -0.48
    はじめに
    -0.48
    POSITIVE LOGITS
    ative
    0.89
    Portail
    0.75
    ATIVE
    0.72
    +#+
    0.65
    atively
    0.64
     xmlns
    0.61
    xmlns
    0.60
     createContext
    0.58
    InjectAttribute
    0.58
    ativity
    0.58
    Activations Density 2.463%

    No Known Activations