© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 6985
    Prev
    Next
    INDEX
    Explanations

    elements related to visual or physical attributes of characters or objects in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.56
    antaranya
    -0.49
    delaide
    -0.44
    berdayakan
    -0.43
    baliknya
    -0.43
    BagConstraints
    -0.42
    ⓧ
    -0.42
     nakalista
    -0.41
    ariConfig
    -0.41
    mbg
    -0.41
    POSITIVE LOGITS
     resembles
    2.42
     resemble
    2.39
     resemblance
    2.22
     resembled
    2.22
     resembling
    2.13
     reminiscent
    2.09
     similarity
    1.97
     resemb
    1.94
     similarities
    1.91
     ressemb
    1.83
    Activations Density 1.137%

    No Known Activations