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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8309
    Prev
    Next
    INDEX
    Explanations

    references to actions or entities that are "behind" something, indicating an interest in underlying factors or backgrounds

    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
     skolan
    -0.51
    |};
    -0.47
     fiscales
    -0.46
     skimage
    -0.46
    instancetype
    -0.45
    konferenz
    -0.44
    JsonFormat
    -0.44
    SYSC
    -0.44
    czegó
    -0.43
     isNameExpr
    -0.43
    POSITIVE LOGITS
     behind
    3.61
    behind
    3.30
     Behind
    3.20
    Behind
    3.14
     BEHIND
    3.06
     detrás
    2.59
     derrière
    2.53
     dietro
    2.23
     bakom
    2.20
     achter
    1.83
    Activations Density 0.106%

    No Known Activations