© 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. 17-GEMMASCOPE-RES-16K
    11. 6856
    Prev
    Next
    INDEX
    Explanations

    technical terms and definitions related to specific processes and components in technical documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vician
    -0.53
     nakalista
    -0.51
     округ
    -0.47
    Configurer
    -0.45
     Administrativna
    -0.44
    posables
    -0.44
    ]').
    -0.44
    ].)
    -0.43
    。
    -0.41
    izowane
    -0.41
    POSITIVE LOGITS
     including
    0.82
    たとえば
    0.80
    verwijspagina
    0.77
    例えば
    0.77
     např
    0.75
     notamment
    0.72
     ovvero
    0.71
    无论是
    0.71
     Including
    0.71
    including
    0.70
    Activations Density 0.364%

    No Known Activations