Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1411
    Prev
    Next
    INDEX
    Explanations

    methods and techniques related to monitoring and measurement systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WireFormatLite
    -0.59
     createSlice
    -0.49
    المكان
    -0.48
     Delano
    -0.47
     circo
    -0.47
     esternos
    -0.45
     kork
    -0.44
     smallest
    -0.44
    Computed
    -0.44
    HttpStatus
    -0.43
    POSITIVE LOGITS
     techniques
    1.29
     Techniques
    1.19
     technique
    1.16
     methods
    1.16
     Technique
    1.09
    techniques
    1.08
     method
    1.07
    methods
    1.02
    Techniques
    1.02
     Methods
    0.99
    Activations Density 0.616%

    No Known Activations