© 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. 25-GEMMASCOPE-RES-16K
    6. 2896
    Prev
    Next
    INDEX
    Explanations

    instructions and recommendations related to practical tasks and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.76
     lẫn
    -0.66
    だったが
    -0.66
    due
    -0.60
     dovuto
    -0.57
     due
    -0.56
     Due
    -0.56
    Due
    -0.55
    omyelitis
    -0.53
     verwe
    -0.53
    POSITIVE LOGITS
     yourself
    1.35
     preferably
    1.13
    preferably
    1.04
    yourself
    1.01
     your
    1.01
     if
    0.96
     yourselves
    0.95
     YOURSELF
    0.91
    your
    0.90
     then
    0.90
    Activations Density 0.597%

    No Known Activations