© 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. 3-GEMMASCOPE-RES-16K
    6. 718
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives or phrases indicating differences in levels or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Manbalar
    -0.51
    gridx
    -0.49
     Faso
    -0.48
    item
    -0.47
    RenderAtEndOf
    -0.46
    イクアウト
    -0.46
    ([...
    -0.46
     provato
    -0.45
    BaseType
    -0.45
    ItemLayout
    -0.44
    POSITIVE LOGITS
    astify
    0.71
    LVANIA
    0.67
    fficio
    0.64
    fficients
    0.64
    SOUNDBITE
    0.64
     Teller
    0.63
    alyptus
    0.59
    piram
    0.59
    /#{
    0.59
    "):
    
    0.59
    Activations Density 0.766%

    No Known Activations