© 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. 38-GEMMASCOPE-RES-16K
    11. 15333
    Prev
    Next
    INDEX
    Explanations

    specific references to individuals' roles and their attributes, particularly in a legal or governmental context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oprot
    -0.44
    icksburg
    -0.44
    CppMethod
    -0.42
    Ӕ
    -0.41
    lägg
    -0.41
     Photocase
    -0.41
    addPreferredGap
    -0.40
    ctose
    -0.40
     CreateTagHelper
    -0.40
     myſelf
    -0.39
    POSITIVE LOGITS
     sal
    3.39
     Sal
    3.30
    Sal
    3.27
     SAL
    3.06
    sal
    3.05
    SAL
    2.86
     Sali
    1.99
     SALV
    1.96
     Sala
    1.95
     Salz
    1.91
    Activations Density 0.881%

    No Known Activations