© 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. 2-GEMMASCOPE-RES-16K
    11. 8432
    Prev
    Next
    INDEX
    Explanations

    references to specific actors or roles 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 @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chwiliwch
    -0.49
    acamata
    -0.43
     alimentaria
    -0.42
     nocturna
    -0.42
     äls
    -0.39
    SizeF
    -0.39
    Composable
    -0.38
     navideñas
    -0.38
     psicológica
    -0.38
    MergeFrom
    -0.38
    POSITIVE LOGITS
     Fel
    0.74
    Fel
    0.71
     fel
    0.71
     Nur
    0.68
    fel
    0.66
     nur
    0.66
     Nit
    0.65
    Nur
    0.65
    Nit
    0.63
     nit
    0.63
    Activations Density 0.543%

    No Known Activations