© 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. 25-GEMMASCOPE-RES-16K
    11. 15502
    Prev
    Next
    INDEX
    Explanations

    narrative elements related to character interactions and emotional responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AttributeSet
    -0.46
    Diweddarwch
    -0.42
     kasarigan
    -0.39
     esternos
    -0.39
    enumii
    -0.37
    </thead>
    -0.37
    HasIndex
    -0.37
     ddelweddau
    -0.36
    SceneManagement
    -0.36
     vinilo
    -0.35
    POSITIVE LOGITS
    posables
    0.44
    Looking
    0.43
    sätzlich
    0.42
     Tilt
    0.41
     Looking
    0.40
    InitVars
    0.39
     helplessly
    0.39
     helpless
    0.39
     Fuck
    0.38
    Pure
    0.38
    Activations Density 0.151%

    No Known Activations