© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 681
    Prev
    Next
    INDEX
    Explanations

    numerical values or dates

    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
    less
    -0.50
    Aten
    -0.47
    zu
    -0.46
     cleaner
    -0.44
     身
    -0.44
     relativement
    -0.43
     emb
    -0.43
     Cleaner
    -0.42
     matang
    -0.42
     penso
    -0.40
    POSITIVE LOGITS
    PreferredItem
    0.89
    клопе
    0.85
    ConstraintMaker
    0.81
    原始内容存档于
    0.80
    Hozzáférés
    0.76
    aarrggbb
    0.74
    URLException
    0.74
    Portail
    0.73
    ValueStyle
    0.71
    StructEnd
    0.70
    Activations Density 0.282%

    No Known Activations