Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 3159
    Prev
    Next
    INDEX
    Explanations

    terms related to biological processes and programming functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.52
    exitRule
    -0.43
    zące
    -0.41
    Available
    -0.41
    zustellen
    -0.39
    Sharing
    -0.38
    needed
    -0.38
    olá
    -0.38
    ರ
    -0.38
    RTLI
    -0.38
    POSITIVE LOGITS
     modified
    1.26
     transformed
    1.26
     amended
    1.17
     revised
    1.17
     altered
    1.16
     renovated
    1.13
     cleansed
    1.12
     repaired
    1.11
     cleaned
    1.10
     upgraded
    1.07
    Activations Density 0.940%

    No Known Activations