© 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. 25-GEMMASCOPE-RES-16K
    11. 6720
    Prev
    Next
    INDEX
    Explanations

    programming concepts and data structure elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    elements related to programming syntax and mathematical expressions

    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
    left
    -1.52
     left
    -1.16
    "]));
    -0.89
     Left
    -0.84
    langle
    -0.83
    right
    -0.81
    "]),
    -0.76
     LEFT
    -0.76
    LEFT
    -0.72
     izquierda
    -0.71
    POSITIVE LOGITS
     ujednoznacz
    0.67
    }}
    0.52
     تانيه
    0.52
    perative
    0.47
    Travelling
    0.47
    Становништво
    0.46
    colare
    0.46
    Charset
    0.46
     fata
    0.45
    principalTable
    0.45
    Activations Density 0.451%

    No Known Activations