© 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. 14-GEMMASCOPE-RES-16K
    6. 5791
    Prev
    Next
    INDEX
    Explanations

    phrases related to lists or sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.50
     ModelAndView
    -0.49
    }></
    -0.46
    ########.
    -0.44
    bukkit
    -0.44
    كذا
    -0.43
    cjon
    -0.43
    ."],
    -0.43
    netty
    -0.42
    Voll
    -0.42
    POSITIVE LOGITS
     secondly
    1.51
     Secondly
    1.45
    Secondly
    1.39
     second
    0.93
    其次
    0.88
     Thirdly
    0.83
    second
    0.83
    enumi
    0.82
     segundo
    0.78
    二是
    0.77
    Activations Density 0.678%

    No Known Activations