© 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. 14-GEMMASCOPE-RES-16K
    11. 8162
    Prev
    Next
    INDEX
    Explanations

    certain categories or specifications related to concepts like types, forms, or characteristics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saira
    -0.41
     Ganzen
    -0.40
    それとも
    -0.38
    chaik
    -0.37
    audiovisuel
    -0.37
     gantung
    -0.36
    usiai
    -0.36
    DebuggerNonUser
    -0.36
    ńst
    -0.36
     Lokales
    -0.35
    POSITIVE LOGITS
     certain
    0.75
    Certain
    0.72
    certain
    0.71
     Certain
    0.70
     certaine
    0.68
     certaines
    0.66
     sommige
    0.64
     unele
    0.60
     bepaalde
    0.60
     niektó
    0.59
    Activations Density 0.404%

    No Known Activations