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. 14-GEMMASCOPE-RES-16K
    6. 7602
    Prev
    Next
    INDEX
    Explanations

    specific references to scientific processes or results in documents

    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
    الحياه
    -0.56
    ViewImports
    -0.54
    BufferException
    -0.48
    ])->
    -0.48
     entire
    -0.48
    ">:
    -0.47
    bottomrule
    -0.47
    ########.
    -0.47
    ">—
    -0.47
    ())));
    -0.46
    POSITIVE LOGITS
    oredCriteria
    0.64
    posedge
    0.64
     månader
    0.55
     dagar
    0.54
     Secondly
    0.54
    +#+#
    0.53
     دیکھیے
    0.53
     Alternatively
    0.52
     Bourgoin
    0.52
     secondly
    0.52
    Activations Density 0.551%

    No Known Activations