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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 15916
    Prev
    Next
    INDEX
    Explanations

    phrases related to mental health issues and support resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 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
     Ax
    -1.66
     AX
    -1.65
     CX
    -1.63
     BX
    -1.62
     OX
    -1.61
    OX
    -1.59
    AX
    -1.58
     getX
    -1.58
     Ox
    -1.58
    IX
    -1.57
    POSITIVE LOGITS
    itinéraire
    0.51
     Pringle
    0.46
    GIVEREF
    0.44
    CppMethod
    0.41
    Enllaces
    0.41
     Clough
    0.40
     Clifford
    0.39
    енча
    0.39
     Coppola
    0.39
     Marien
    0.38
    Activations Density 3.843%

    No Known Activations